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

    Neuronpedia

    INDEX
    Explanations

    scientific references and publications, particularly related to physics

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

    Tokens followed by a capital letter

    np_acts-logits-general · gemini-2.0-flash

    starting position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }{*}{}
    -0.96
     HasFactory
    -0.93
    -0.91
    __':
    -0.91
     متعلقه
    -0.86
    __':
    -0.86
    InstanceState
    -0.85
    Cyfeiriadau
    -0.84
     للمعارف
    -0.83
    GIVEREF
    -0.82
    POSITIVE LOGITS
     Pals
    0.78
    P
    0.74
     P
    0.68
     Pn
    0.67
     plainte
    0.66
    Ps
    0.62
    PA
    0.62
     Pirates
    0.61
     PSS
    0.61
     Panthers
    0.60
    Act Density 3.350%

    No Known Activations