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

    Neuronpedia

    INDEX
    Explanations

    Goals and self-improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encil
    -0.06
    Interior
    -0.06
    scious
    -0.06
    LU
    -0.06
    JO
    -0.06
    婚
    -0.06
    KEEP
    -0.06
     tiên
    -0.06
    err
    -0.05
    的小
    -0.05
    POSITIVE LOGITS
    τηγορ
    0.07
    ulação
    0.07
    pole
    0.06
    ções
    0.06
     Inherits
    0.06
    继
    0.06
    eygamber
    0.06
     casing
    0.06
     integ
    0.06
    ί
    0.06
    Act Density 0.217%

    No Known Activations