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
     Central
    -0.07
    ultimate
    -0.07
    gas
    -0.07
     Parks
    -0.07
     graft
    -0.07
    gles
    -0.07
    资源配置
    -0.07
    "P
    -0.07
    esthesia
    -0.07
     aldı
    -0.06
    POSITIVE LOGITS
    MOVED
    0.07
     tb
    0.06
    弃
    0.06
     patched
    0.06
    Combo
    0.06
    Fixed
    0.06
    [code
    0.06
    퍅
    0.06
    ﰁ
    0.06
    _float
    0.06
    Act Density 0.000%

    No Known Activations