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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boBox
    -0.06
     since
    -0.06
    prog
    -0.06
    168
    -0.06
    로는
    -0.06
    ूक
    -0.06
     fearful
    -0.06
     if
    -0.05
    Home
    -0.05
    ilmiş
    -0.05
    POSITIVE LOGITS
    toggleClass
    0.08
    สภ
    0.07
     sublic
    0.07
     IsPlainOldData
    0.07
    -tech
    0.07
     tokenizer
    0.07
    istics
    0.06
    ENCE
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
     全
    0.06
    Act Density 0.096%

    No Known Activations