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

    Neuronpedia

    INDEX
    Explanations

    code/identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уста
    -0.07
     xứ
    -0.07
    (tcp
    -0.07
    ===============
    -0.06
    -photo
    -0.06
     pau
    -0.06
    �
    -0.06
    浦
    -0.06
     май
    -0.06
    ρίς
    -0.06
    POSITIVE LOGITS
     Conf
    0.06
    orks
    0.06
     Trailer
    0.06
    (tr
    0.06
    gressive
    0.06
    iciencies
    0.06
    ская
    0.06
    ificación
    0.06
    اعات
    0.06
    iating
    0.05
    Act Density 0.001%

    No Known Activations