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

    Neuronpedia

    INDEX
    Explanations

    first-person perspective expressions

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

    we it i let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.71
    -0.71
    таратура
    -0.67
     Numerade
    -0.65
    featureID
    -0.64
    -------
    -0.63
    TagMode
    -0.61
    twimg
    -0.61
    Билгалдахарш
    -0.60
    StoryboardSegue
    -0.60
    POSITIVE LOGITS
    2
    0.40
    3
    0.40
     Suecia
    0.39
     "
    0.39
     Petrov
    0.36
    enable
    0.36
    4
    0.36
    8
    0.35
    1
    0.35
    0
    0.35
    Act Density 0.205%

    No Known Activations