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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    звичай
    -0.06
    _MAP
    -0.06
     ecommerce
    -0.06
     mesure
    -0.06
    锦
    -0.06
     deferred
    -0.06
    _tool
    -0.06
     cực
    -0.06
     березня
    -0.06
     prudent
    -0.06
    POSITIVE LOGITS
    Alexander
    0.07
    .cols
    0.07
    ,T
    0.07
     waterproof
    0.06
     Dak
    0.06
     honored
    0.06
     Alexander
    0.06
    &t
    0.06
    ))]
    0.06
     bào
    0.06
    Act Density 0.053%

    No Known Activations