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
    ướng
    -0.08
    𨱏
    -0.07
    ekt
    -0.07
    ieber
    -0.07
    ex
    -0.07
     learning
    -0.07
     addiction
    -0.07
     kd
    -0.06
    迎接
    -0.06
    密切
    -0.06
    POSITIVE LOGITS
    	reg
    0.08
    ’util
    0.07
    _snd
    0.07
    LOCKS
    0.07
     Chủ
    0.07
    𫓶
    0.07
    _IMAGES
    0.06
    ('\\
    0.06
    .onerror
    0.06
    OUNTRY
    0.06
    Act Density 0.003%

    No Known Activations