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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    无
    -0.07
    不见
    -0.07
    Rnd
    -0.07
    🤧
    -0.06
     Prison
    -0.06
    UNK
    -0.06
    К
    -0.06
    헛
    -0.06
    TYPE
    -0.06
     ToolStrip
    -0.06
    POSITIVE LOGITS
     Bourbon
    0.08
    cstdlib
    0.07
    arine
    0.07
    عادة
    0.07
    fcc
    0.07
    orientation
    0.07
     issu
    0.07
    弹性
    0.07
     pen
    0.06
     Premiere
    0.06
    Act Density 0.006%

    No Known Activations