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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ад
    -0.07
     relent
    -0.07
    巩
    -0.07
     WILL
    -0.06
    �
    -0.06
    驼
    -0.06
    ご紹
    -0.06
    �
    -0.06
     özelliği
    -0.06
     bluff
    -0.06
    POSITIVE LOGITS
    .DATE
    0.07
    trees
    0.07
    _kwargs
    0.07
    .week
    0.07
    Changing
    0.07
    Reach
    0.07
     ammunition
    0.07
    מעשה
    0.06
    _dicts
    0.06
    ('*',
    0.06
    Act Density 0.008%

    No Known Activations