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

    Neuronpedia

    INDEX
    Explanations

    Renaming/rebranding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Developed
    -0.07
     shape
    -0.07
    ﯶ
    -0.07
     trophies
    -0.07
    陌生人
    -0.07
    _boxes
    -0.06
     "#
    -0.06
     formulas
    -0.06
    师事务
    -0.06
     spaces
    -0.06
    POSITIVE LOGITS
    ŗ
    0.07
    حت
    0.07
     VALID
    0.07
     поб
    0.07
    $total
    0.07
    ٪
    0.07
     slew
    0.07
    [selected
    0.07
    pur
    0.06
     доволь
    0.06
    Act Density 0.044%

    No Known Activations