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

    Neuronpedia

    INDEX
    Explanations

    believed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getString
    -0.07
    anguages
    -0.07
     ficken
    -0.07
    ้ท
    -0.07
     výstav
    -0.07
     cạnh
    -0.07
     cra
    -0.07
    extended
    -0.06
    aturday
    -0.06
     Cz
    -0.06
    POSITIVE LOGITS
     Bel
    0.09
    belie
    0.08
     πολύ
    0.08
     believe
    0.08
     بل
    0.07
    Bel
    0.07
     believed
    0.07
     believing
    0.07
     believes
    0.07
    ב
    0.07
    Act Density 0.032%

    No Known Activations