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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ائمة
    -0.07
     veces
    -0.07
     questi
    -0.07
     présent
    -0.07
     modifying
    -0.07
     Yu
    -0.07
    ْم
    -0.07
     HIV
    -0.07
     producing
    -0.06
    (Collision
    -0.06
    POSITIVE LOGITS
     <",
    0.07
    .school
    0.07
     navr
    0.07
    컬
    0.06
     الأف
    0.06
    -mark
    0.06
     �
    0.06
    .labelX
    0.06
     노
    0.06
    리로
    0.06
    Act Density 0.003%

    No Known Activations