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

    Neuronpedia

    INDEX
    Explanations

    references to personal rights and claims related to access or support

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

    followed by modal verbs

    np_acts-logits-general · gemini-2.0-flash

    having or not having

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hObject
    -0.49
     EdgeInsets
    -0.46
    Swar
    -0.45
     stay
    -0.44
    ()
    -0.44
    irmanship
    -0.43
    økt
    -0.43
    Portale
    -0.43
    Intended
    -0.43
     препратки
    -0.41
    POSITIVE LOGITS
     possessed
    1.03
     possess
    0.99
     habet
    0.98
     dimiliki
    0.97
     memili
    0.95
     posiad
    0.94
     possède
    0.92
     possesses
    0.92
     memiliki
    0.88
    having
    0.88
    Act Density 0.269%

    No Known Activations