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
     hospitality
    -0.07
    活动
    -0.06
     또한
    -0.06
     properties
    -0.06
     silly
    -0.06
     Vanilla
    -0.06
     Prospect
    -0.06
    -season
    -0.06
    bad
    -0.06
    Folder
    -0.06
    POSITIVE LOGITS
     nejd
    0.07
    ──
    0.07
    	↵	↵	↵	↵
    0.07
    ldkf
    0.06
    pciones
    0.06
    _minus
    0.06
     {↵↵↵↵
    0.06
    .RowHeaders
    0.06
    enght
    0.06
    혁
    0.06
    Act Density 0.021%

    No Known Activations