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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     програ
    -0.07
    ocaly
    -0.07
     гра
    -0.07
    (record
    -0.06
     филь
    -0.06
     revolver
    -0.06
     tren
    -0.06
     Pend
    -0.06
    (candidate
    -0.06
    Pitch
    -0.06
    POSITIVE LOGITS
    .#
    0.07
     BRE
    0.07
    illon
    0.07
    RE
    0.06
    .E
    0.06
    #/
    0.06
    /I
    0.06
    拉
    0.06
    ['__
    0.06
     calling
    0.06
    Act Density 0.028%

    No Known Activations