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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest or curiosity

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

    expresses personal interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.52
     _$
    -0.52
    Whe
    -0.51
    благо
    -0.51
    ตร์
    -0.49
    MergeFrom
    -0.48
    chability
    -0.48
    rieu
    -0.48
    dh
    -0.48
    reactstrap
    -0.47
    POSITIVE LOGITS
    INTEREST
    0.97
    interes
    0.90
     INTEREST
    0.89
    interested
    0.87
     interest
    0.87
     Interest
    0.85
     interested
    0.85
    Interested
    0.84
    interest
    0.82
    Interest
    0.82
    Act Density 0.056%

    No Known Activations