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

    Neuronpedia

    INDEX
    Explanations

    Code layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ata
    -0.07
     SD
    -0.07
     exile
    -0.06
    Abs
    -0.06
    _stack
    -0.06
     RCA
    -0.06
    [@
    -0.06
    _invalid
    -0.06
    .Fatal
    -0.06
    ¨ط
    -0.06
    POSITIVE LOGITS
     پژ
    0.06
     визнач
    0.06
     Feder
    0.06
    PAGE
    0.06
     confusion
    0.06
     �
    0.06
    ظه
    0.06
    اية
    0.06
    rene
    0.06
    $options
    0.06
    Act Density 0.039%

    No Known Activations