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

    Neuronpedia

    INDEX
    Explanations

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cache
    -0.07
    /ros
    -0.07
    Save
    -0.07
    -producing
    -0.07
    唱
    -0.06
     allocator
    -0.06
    schemas
    -0.06
    _numbers
    -0.06
    hashCode
    -0.06
     shaved
    -0.06
    POSITIVE LOGITS
     Attend
    0.07
     Week
    0.06
     ÜNİ
    0.06
    Replacing
    0.06
    _IList
    0.06
     Diamond
    0.06
     関
    0.06
    出售
    0.06
     MAIL
    0.06
    �프
    0.06
    Act Density 0.032%

    No Known Activations