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

    Neuronpedia

    INDEX
    Explanations

    Reducing, taking away

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کار
    -0.06
    MOOTH
    -0.06
     роль
    -0.06
    antu
    -0.06
     kg
    -0.06
     pastry
    -0.06
    脸
    -0.06
     Convention
    -0.06
    ことは
    -0.05
    .intro
    -0.05
    POSITIVE LOGITS
    (textBox
    0.07
     PLATFORM
    0.07
     WATCH
    0.07
    _HISTORY
    0.07
    _questions
    0.07
    shiv
    0.07
    neath
    0.07
    xxxx
    0.07
    .ViewHolder
    0.06
     registered
    0.06
    Act Density 0.049%

    No Known Activations