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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    즘
    -0.07
    冷库
    -0.07
     succession
    -0.07
     Sul
    -0.07
    formatter
    -0.06
     Kol
    -0.06
     vapor
    -0.06
     packets
    -0.06
    ylan
    -0.06
     Cv
    -0.06
    POSITIVE LOGITS
     stron
    0.07
    грани
    0.07
    ечно
    0.07
    处在
    0.07
    قن
    0.07
    全部
    0.07
    逶
    0.07
    .Double
    0.06
     Boundary
    0.06
    survey
    0.06
    Act Density 0.000%

    No Known Activations