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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aplikace
    -0.08
     léka
    -0.07
    pictured
    -0.07
     vect
    -0.06
     beberapa
    -0.06
    IALIZ
    -0.06
     soften
    -0.06
    лед
    -0.06
    vect
    -0.06
     ifade
    -0.06
    POSITIVE LOGITS
    cision
    0.07
    اگ
    0.06
    outcome
    0.06
     оно
    0.06
    mu
    0.06
    ovým
    0.06
    گاه
    0.06
    error
    0.06
     #[
    0.06
     putting
    0.06
    Act Density 0.013%

    No Known Activations