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

    Neuronpedia

    INDEX
    Explanations

    complex language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manner
    -0.07
    CLIENT
    -0.07
    ázky
    -0.06
    damage
    -0.06
    去
    -0.06
     thiếu
    -0.06
     silver
    -0.06
    ystack
    -0.06
     Telefon
    -0.06
     Medicare
    -0.06
    POSITIVE LOGITS
    .GPIO
    0.08
    (pd
    0.07
    .jackson
    0.07
     Cube
    0.07
     ejac
    0.06
     تكييف
    0.06
    (pin
    0.06
    -prof
    0.06
    _def
    0.06
     کنترل
    0.06
    Act Density 0.342%

    No Known Activations