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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ห
    -0.07
     品
    -0.07
    _imag
    -0.06
     subdir
    -0.06
    coc
    -0.06
    ｰ
    -0.06
    .oracle
    -0.06
    �
    -0.06
     Composer
    -0.06
     пацієн
    -0.06
    POSITIVE LOGITS
    划
    0.07
    老师
    0.06
    を開
    0.06
    rays
    0.06
     desirable
    0.06
    願
    0.06
    Remaining
    0.06
    abilidad
    0.06
     circles
    0.06
     occupies
    0.06
    Act Density 0.009%

    No Known Activations