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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	JPanel
    -0.07
    .Animation
    -0.06
    Under
    -0.06
     studios
    -0.06
    excluding
    -0.06
    楽しい
    -0.06
     Honest
    -0.06
    をご
    -0.06
     jealousy
    -0.06
    errorCode
    -0.06
    POSITIVE LOGITS
     compounds
    0.07
    분
    0.07
    _STA
    0.07
    多重
    0.07
    пле
    0.07
    XA
    0.07
    iciente
    0.07
     mitig
    0.07
    ('.')↵
    0.07
    贯通
    0.07
    Act Density 0.004%

    No Known Activations