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

    Neuronpedia

    INDEX
    Explanations

    Pool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bras
    -0.07
    ohan
    -0.06
    /music
    -0.06
    的事
    -0.06
    ('')↵
    -0.06
     catalogue
    -0.06
    file
    -0.06
    :false
    -0.06
    .ops
    -0.06
    expr
    -0.06
    POSITIVE LOGITS
     Pres
    0.07
    _subscribe
    0.07
     Alexandre
    0.06
     Druid
    0.06
    fce
    0.06
     unidades
    0.06
     Poe
    0.06
    _dr
    0.06
    Mut
    0.06
    Areas
    0.06
    Act Density 0.001%

    No Known Activations