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

    Neuronpedia

    INDEX
    Explanations

    avoid damage/heat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptom
    -0.07
    輯
    -0.07
    歧
    -0.07
    neg
    -0.07
     hük
    -0.06
     beliefs
    -0.06
     الفلسطينية
    -0.06
    inge
    -0.06
    mony
    -0.06
    胜负
    -0.06
    POSITIVE LOGITS
     machines
    0.07
     Bombay
    0.07
     Supplies
    0.07
    ATFORM
    0.07
    𝒃
    0.07
     ООО
    0.07
     equipment
    0.07
    _MS
    0.06
    probe
    0.06
    ↵
    0.06
    Act Density 0.006%

    No Known Activations