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

    Neuronpedia

    INDEX
    Explanations

    pic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moins
    -0.06
     erotisch
    -0.06
     Pro
    -0.06
     verdad
    -0.06
     swirling
    -0.06
    piar
    -0.06
    	window
    -0.06
    大会
    -0.06
     mf
    -0.06
     cfg
    -0.06
    POSITIVE LOGITS
     TEntity
    0.07
     Marilyn
    0.06
    _BIT
    0.06
    .Action
    0.06
     ASC
    0.06
     alcuni
    0.06
    /octet
    0.06
    ‑
    0.06
    ahas
    0.06
     поруш
    0.06
    Act Density 0.002%

    No Known Activations