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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Formation
    -0.07
    bindValue
    -0.07
    َف
    -0.07
    ureau
    -0.06
    nds
    -0.06
     commence
    -0.06
    unky
    -0.06
    Dat
    -0.06
     فريق
    -0.06
    iry
    -0.06
    POSITIVE LOGITS
    .addTarget
    0.08
    Translated
    0.07
     skyrocket
    0.07
     카지노
    0.07
    غة
    0.06
    612
    0.06
     woven
    0.06
     الص
    0.06
     والأ
    0.06
     ABC
    0.06
    Act Density 0.012%

    No Known Activations