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

    Neuronpedia

    INDEX
    Explanations

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    为
    -0.07
     директор
    -0.06
    ました
    -0.06
    _android
    -0.06
     sacrificing
    -0.06
    92
    -0.06
     Norfolk
    -0.06
    prt
    -0.06
     Manager
    -0.06
    ้อ
    -0.06
    POSITIVE LOGITS
    	Start
    0.07
     stě
    0.06
     frac
    0.06
    respuesta
    0.06
     レ
    0.06
    (eval
    0.06
     railing
    0.06
    .Expressions
    0.06
    endcode
    0.06
    ября
    0.06
    Act Density 0.342%

    No Known Activations