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

    Neuronpedia

    INDEX
    Explanations

    ten

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reynolds
    -0.07
     Dry
    -0.07
     felse
    -0.06
     tex
    -0.06
    //------------------------------------------------------------------------------↵↵
    -0.06
    aniem
    -0.06
    女性
    -0.06
    checker
    -0.06
     currencies
    -0.06
    brig
    -0.06
    POSITIVE LOGITS
     sdf
    0.07
    .SM
    0.07
    -style
    0.07
     tissues
    0.07
    กำ
    0.07
    Prot
    0.06
     sitio
    0.06
     fierce
    0.06
     thử
    0.06
    _line
    0.06
    Act Density 0.010%

    No Known Activations