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

    Neuronpedia

    INDEX
    Explanations

    df

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potion
    -0.07
    ”.↵↵
    -0.07
    ).↵↵↵
    -0.07
     volte
    -0.07
     Hispanics
    -0.06
    ('(
    -0.06
    billing
    -0.06
     ambiance
    -0.06
    azione
    -0.06
     XElement
    -0.06
    POSITIVE LOGITS
    弟
    0.07
     مدر
    0.07
    STER
    0.06
    df
    0.06
     Holt
    0.06
    ngr
    0.06
     RDF
    0.06
    (COLOR
    0.06
    الى
    0.06
    DDL
    0.06
    Act Density 0.006%

    No Known Activations