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

    Neuronpedia

    INDEX
    Explanations

    Code or programming language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    variables
    -0.06
     Jones
    -0.06
     кер
    -0.06
    _DEFINE
    -0.06
    _HEL
    -0.06
    (atom
    -0.06
     accounting
    -0.06
    een
    -0.06
    support
    -0.06
    _CNT
    -0.06
    POSITIVE LOGITS
     bilinen
    0.06
     nieu
    0.06
    Dash
    0.06
     sham
    0.06
    €
    0.06
     ^{°}
    0.06
    ..<
    0.06
    (U
    0.06
    ์ได
    0.06
    Moreover
    0.06
    Act Density 0.000%

    No Known Activations