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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ýt
    -0.07
    xCE
    -0.07
    鄣
    -0.07
    .IsNullOr
    -0.07
     hastalık
    -0.07
    יז
    -0.07
     GLint
    -0.07
     jit
    -0.07
    茺
    -0.07
    ierge
    -0.07
    POSITIVE LOGITS
     Douglas
    0.08
     sw
    0.07
    entropy
    0.07
     Play
    0.07
    ...
↵
    0.07
    桌面
    0.07
     כנגד
    0.07
    规格
    0.07
     PROM
    0.07
     数据
    0.07
    Act Density 0.006%

    No Known Activations