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

    Neuronpedia

    INDEX
    Explanations

    Measurements/analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    лок
    -0.07
    _sec
    -0.06
     assassin
    -0.06
     populist
    -0.06
    _pemb
    -0.06
    /music
    -0.06
    lbrace
    -0.06
    _EQUAL
    -0.06
     Refriger
    -0.06
    POSITIVE LOGITS
    ään
    0.07
    ouncement
    0.07
    abei
    0.07
     прог
    0.06
     Clara
    0.06
     pave
    0.06
    ZN
    0.06
    heure
    0.06
     Также
    0.06
     decorate
    0.06
    Act Density 0.059%

    No Known Activations