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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teenagers
    -0.09
     teenager
    -0.08
     Warm
    -0.08
     �
    -0.08
     teens
    -0.08
    _shape
    -0.08
    年轻
    -0.08
     Preconditions
    -0.08
     toddlers
    -0.08
    _thr
    -0.08
    POSITIVE LOGITS
    転載
    0.14
     unauthorized
    0.12
    転載は禁止
    0.12
    版权
    0.12
     copyrighted
    0.12
     copyright
    0.12
    转载
    0.11
    Unauthorized
    0.11
     copyrights
    0.11
    转载请
    0.11
    Act Density 0.032%

    No Known Activations