Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    features related to safety and aesthetic value in contexts of design or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding square brackets

    np_acts-logits-general · gemini-2.0-flash

    simultaneously, also, along with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     challenger
    -0.54
    AndEndTag
    -0.52
    Personendaten
    -0.52
    XmlAccessType
    -0.51
     resourceCulture
    -0.49
    Chall
    -0.47
    IUrlHelper
    -0.47
     الحره
    -0.46
    __*/
    -0.46
     beginnetje
    -0.46
    POSITIVE LOGITS
     sekaligus
    1.11
     zugleich
    1.09
    顺便
    0.98
    兼
    0.97
     gleichzeitig
    0.91
     zároveň
    0.91
     tevens
    0.89
     samtidig
    0.87
     also
    0.85
     ulterior
    0.84
    Act Density 0.483%

    No Known Activations