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
    .dup
    -0.07
    _distribution
    -0.06
     مه
    -0.06
     PACK
    -0.06
     dust
    -0.06
    verts
    -0.06
     names
    -0.06
    �
    -0.06
     thrive
    -0.06
    .Event
    -0.06
    POSITIVE LOGITS
     skating
    0.06
    !↵↵
    0.06
     окон
    0.06
    ¤¤
    0.06
    rompt
    0.06
     ")"
    0.06
    ोश
    0.06
    लत
    0.06
    EDGE
    0.06
     새글
    0.06
    Act Density 0.013%

    No Known Activations