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

    Neuronpedia

    INDEX
    Explanations

    the word "impact" and associated negative words

    oai_token-act-pair · gemini-2.0-flash

    impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impact
    -2.89
    impact
    -2.64
    Impact
    -2.59
     Impact
    -2.58
     impacts
    -2.23
     impacto
    -2.22
     IMPACT
    -2.08
     Impacts
    -1.98
    IMPACT
    -1.95
    Impacts
    -1.90
    POSITIVE LOGITS
    setVerticalGroup
    0.62
    Hochspringen
    0.56
    omości
    0.54
    :✨
    0.52
    ArgsConstructor
    0.52
    fordshire
    0.52
    ;->
    0.52
    NVIC
    0.51
    yakarta
    0.51
    bhan
    0.51
    Act Density 0.485%

    No Known Activations