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

    Neuronpedia

    INDEX
    Explanations

    exponents and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zonas
    -0.08
    .Buffer
    -0.07
    kań
    -0.07
     Blocking
    -0.07
     Notifications
    -0.07
     BF
    -0.07
     zona
    -0.07
     परिसर
    -0.07
     হয়ে
    -0.07
     🙂
    -0.07
    POSITIVE LOGITS
     exponent
    0.10
    ETHOD
    0.09
     طويلة
    0.09
     ಪದ
    0.09
     mandated
    0.09
     drukken
    0.08
     jooksul
    0.08
    齢
    0.08
     täht
    0.08
     sufficiently
    0.08
    Act Density 0.036%

    No Known Activations