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

    Neuronpedia

    INDEX
    Explanations

    Financial losses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tess
    -0.07
    er
    -0.07
     river
    -0.07
    ms
    -0.07
    ATFORM
    -0.06
    laş
    -0.06
    IEnumerator
    -0.06
    elfare
    -0.06
     bilin
    -0.06
    Token
    -0.06
    POSITIVE LOGITS
     ingres
    0.07
    ieces
    0.06
     Catholic
    0.06
     Shanghai
    0.06
     racks
    0.06
     aggravated
    0.06
     inicio
    0.06
    /products
    0.06
    \Lib
    0.06
     MTV
    0.06
    Act Density 0.019%

    No Known Activations