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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Department
    -0.07
     formatted
    -0.06
     authored
    -0.06
     Widgets
    -0.06
     without
    -0.06
     violates
    -0.06
    _RETRY
    -0.06
    tright
    -0.06
     इसस
    -0.06
     MIS
    -0.06
    POSITIVE LOGITS
     ${(
    0.07
    tek
    0.07
    یشه
    0.07
    ンド
    0.06
     applaud
    0.06
    ,alpha
    0.06
    ray
    0.06
     ワ
    0.06
    .browser
    0.06
     SRC
    0.06
    Act Density 0.001%

    No Known Activations