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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    폄
    -0.07
    __':
↵
    -0.07
     onze
    -0.07
    ԓ
    -0.07
    ㈲
    -0.07
    ⚟
    -0.07
     weakSelf
    -0.07
    쑻
    -0.07
     +#+
    -0.06
     Obviously
    -0.06
    POSITIVE LOGITS
     iconic
    0.08
    疗效
    0.08
     legislative
    0.08
     שירותי
    0.07
    顾虑
    0.07
     bibli
    0.07
    兴起
    0.07
     часто
    0.07
    海南
    0.07
     rugs
    0.07
    Act Density 0.139%

    No Known Activations