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

    Neuronpedia

    INDEX
    Explanations

    Respond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    структор
    -0.07
     #'
    -0.07
     Initially
    -0.07
     ";"
    -0.07
    γι
    -0.07
    nio
    -0.06
    ,mid
    -0.06
    zee
    -0.06
    لل
    -0.06
     gracious
    -0.06
    POSITIVE LOGITS
    电视
    0.07
     закры
    0.07
     ------------------------------------------------------------
    0.06
     meilleure
    0.06
     divisor
    0.06
     principle
    0.06
    _message
    0.06
    Preferred
    0.06
    AGMA
    0.06
    laces
    0.06
    Act Density 0.000%

    No Known Activations