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

    Neuronpedia

    INDEX
    Explanations

    question and answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ાભ
    -0.08
    ­ment
    -0.08
     السيطرة
    -0.08
    Ы
    -0.08
    ammlung
    -0.08
    uang
    -0.08
    ifying
    -0.07
     অভ
    -0.07
     Crap
    -0.07
    имент
    -0.07
    POSITIVE LOGITS
     clarified
    0.10
     clarify
    0.10
     clar
    0.09
     answered
    0.09
     ചോദ
    0.08
     regarding
    0.08
     esclare
    0.08
    clar
    0.07
    aria
    0.07
     ask
    0.07
    Act Density 0.006%

    No Known Activations