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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бон
    -0.07
     oily
    -0.07
     intensely
    -0.07
     recherche
    -0.07
    Hillary
    -0.07
     Gordon
    -0.07
     Corpor
    -0.06
    ペン
    -0.06
    𬳵
    -0.06
    Rock
    -0.06
    POSITIVE LOGITS
     plausible
    0.08
    的
    0.07
     valid
    0.07
     �
    0.07
     Validation
    0.07
     Variant
    0.07
    槃
    0.06
    改革
    0.06
     attained
    0.06
    堡
    0.06
    Act Density 0.024%

    No Known Activations