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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    り
    -0.07
    ctp
    -0.07
    _overlap
    -0.07
    .Selection
    -0.06
     Darth
    -0.06
    (!(
    -0.06
     assignments
    -0.06
     saber
    -0.06
    ्वप
    -0.06
    ΡΑ
    -0.06
    POSITIVE LOGITS
     triang
    0.07
     WX
    0.06
    circ
    0.06
    _Open
    0.06
     avanz
    0.06
     Ribbon
    0.06
    _valor
    0.06
    ǐ
    0.06
     stopped
    0.06
    .Te
    0.06
    Act Density 0.007%

    No Known Activations