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

    Neuronpedia

    INDEX
    Explanations

    Foreign names/words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Presidents
    -0.08
    380
    -0.07
     प्रक
    -0.07
     bers
    -0.07
     खुले
    -0.07
     अध्ययन
    -0.07
     연
    -0.07
    438
    -0.07
     automobile
    -0.07
     চ
    -0.07
    POSITIVE LOGITS
     �
    0.08
     девушка
    0.08
    .sal
    0.08
     Crane
    0.08
     Vik
    0.08
    們
    0.08
    ’ll
    0.08
    Cre
    0.08
     Mab
    0.08
     девушки
    0.08
    Act Density 0.167%

    No Known Activations