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

    Neuronpedia

    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    त
    -0.07
     practically
    -0.07
    /{{
    -0.07
     Bread
    -0.06
     ديگر
    -0.06
     берез
    -0.06
     başında
    -0.06
     Smoke
    -0.06
    Calls
    -0.06
    adaş
    -0.06
    POSITIVE LOGITS
     irre
    0.07
     irreversible
    0.07
     profitability
    0.06
     abuses
    0.06
    데이트
    0.06
     closer
    0.06
    pc
    0.06
    _dims
    0.06
    _SURFACE
    0.06
    >V
    0.06
    Act Density 0.006%

    No Known Activations