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

    Neuronpedia

    INDEX
    Explanations

    trash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olta
    -0.07
    006
    -0.07
    (requestCode
    -0.07
     Âu
    -0.06
    hora
    -0.06
     ciddi
    -0.06
    etting
    -0.06
     während
    -0.06
    dıkları
    -0.06
     nejlepší
    -0.06
    POSITIVE LOGITS
     substrate
    0.07
    暖
    0.06
     redux
    0.06
    庭
    0.06
    شود
    0.06
     تلاش
    0.06
     год
    0.06
    uded
    0.06
    عه
    0.06
     Gaza
    0.06
    Act Density 0.000%

    No Known Activations