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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     oceans
    -0.06
    _MUT
    -0.06
     Hait
    -0.06
    (concat
    -0.06
    _BASE
    -0.06
     �
    -0.06
    ﺪ
    -0.06
     �
    -0.06
    
    -0.06
    POSITIVE LOGITS
    ۱۹۶
    0.07
    qualification
    0.06
     Argument
    0.06
    PJ
    0.06
    ications
    0.06
    .features
    0.06
    旅游
    0.06
     Ivory
    0.06
    -Bar
    0.06
    identification
    0.06
    Act Density 0.003%

    No Known Activations