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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    軍
    -0.07
    _prob
    -0.07
    ot
    -0.07
     volunteering
    -0.07
    -free
    -0.06
    чес
    -0.06
    му
    -0.06
     cov
    -0.06
    決
    -0.06
    Seed
    -0.06
    POSITIVE LOGITS
     michael
    0.07
     Nashville
    0.06
    .orientation
    0.06
     наруш
    0.06
    íř
    0.06
    241
    0.06
    umatic
    0.06
    assemble
    0.06
    .MOUSE
    0.06
    jišť
    0.06
    Act Density 0.064%

    No Known Activations