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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve pointing or indicating directions

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

    pointing and arrows indicating direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rob
    -0.35
    异
    -0.32
    Rob
    -0.30
     risk
    -0.28
    Therefore
    -0.28
     corporate
    -0.28
    الحياه
    -0.27
     impresión
    -0.27
    ouch
    -0.26
     novel
    -0.26
    POSITIVE LOGITS
     estekak
    0.89
     noDo
    0.88
    ScopeManager
    0.78
    writeFieldEnd
    0.78
    GIVEREF
    0.77
    IVEREF
    0.75
     Chwiliwch
    0.75
    AutoField
    0.73
    IsContent
    0.73
    makeConstraints
    0.73
    Act Density 0.068%

    No Known Activations