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

    Neuronpedia

    INDEX
    Explanations

    Grammatical content/negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impending
    -0.07
    ulong
    -0.06
     cubic
    -0.06
    *l
    -0.06
    _LITERAL
    -0.06
    ));//
    -0.06
    .exports
    -0.06
     oxidation
    -0.06
     thiểu
    -0.06
    *z
    -0.06
    POSITIVE LOGITS
     <<<
    0.07
     �
    0.06
     Open
    0.06
    (ml
    0.06
    conversation
    0.06
    naire
    0.06
    」「
    0.06
     Doll
    0.06
    емого
    0.06
     ๆ
    0.06
    Act Density 0.000%

    No Known Activations