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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to data handling and processing systems

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

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.81
    IUrlHelper
    -0.75
    aarrggbb
    -0.74
    IVEREF
    -0.73
    WriteTagHelper
    -0.71
     tartalomajánló
    -0.70
     ſte
    -0.70
     autorytatywna
    -0.68
     مرئيه
    -0.68
     nakalista
    -0.68
    POSITIVE LOGITS
     (
    0.53
     is
    0.48
     when
    0.45
     forhold
    0.45
     they
    0.45
     will
    0.44
                                   
    0.44
     Administración
    0.43
     mogelijkheid
    0.43
     either
    0.43
    Act Density 0.030%

    No Known Activations