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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цьому
    -0.07
    Front
    -0.07
     );
    -0.06
    .theta
    -0.06
    [var
    -0.06
     Swords
    -0.06
     Notification
    -0.06
     })↵
    -0.06
    hyp
    -0.06
     interpol
    -0.06
    POSITIVE LOGITS
    ิงห
    0.07
    něné
    0.07
     wlan
    0.07
     آل
    0.07
     učitel
    0.07
    abilité
    0.06
    monton
    0.06
    ā
    0.06
     cậu
    0.06
    modelo
    0.06
    Act Density 0.015%

    No Known Activations