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

    Neuronpedia

    INDEX
    Explanations

    probable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provision
    -0.07
     lobbying
    -0.06
     CHARSET
    -0.06
     ces
    -0.06
    <ID
    -0.06
     IRS
    -0.06
    stit
    -0.06
     resposta
    -0.06
     Provision
    -0.06
     Sutton
    -0.06
    POSITIVE LOGITS
     probable
    0.09
     exact
    0.07
     *----------------------------------------------------------------
    0.07
    bei
    0.06
    much
    0.06
     nervous
    0.06
     moderately
    0.06
    be
    0.06
    olute
    0.06
    plate
    0.06
    Act Density 0.004%

    No Known Activations