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

    Neuronpedia

    INDEX
    Explanations

    actions or behaviors involving touching or physical interaction

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

    Actions involving physical contact

    np_acts-logits-general · gemini-2.0-flash

    vigorous physical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    킬
    -0.41
    vocable
    -0.40
     default
    -0.40
    сп
    -0.40
     utama
    -0.39
    <i>
    -0.39
     myö
    -0.38
     Multipart
    -0.37
    сий
    -0.37
    Osob
    -0.36
    POSITIVE LOGITS
    ReusableCell
    0.99
     vigorously
    0.93
     furiously
    0.90
     incessantly
    0.86
    PreferredItem
    0.83
     frantically
    0.81
     away
    0.78
    WriteBarrier
    0.77
    DebuggerNonUser
    0.77
     NavController
    0.75
    Act Density 0.175%

    No Known Activations