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

    Neuronpedia

    INDEX
    Explanations

    mathematical or code-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🏃
    -0.07
    �
    -0.07
    badge
    -0.07
    權
    -0.07
    ])]↵
    -0.07
    /INFO
    -0.07
    ReadOnly
    -0.07
    [idx
    -0.06
    寂静
    -0.06
    .pa
    -0.06
    POSITIVE LOGITS
     celebrations
    0.08
     forecasting
    0.07
     SECURITY
    0.07
    דרך
    0.07
    -products
    0.07
     barrier
    0.06
    텁
    0.06
    cząc
    0.06
     Statement
    0.06
     considers
    0.06
    Act Density 0.009%

    No Known Activations