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

    Neuronpedia

    INDEX
    Explanations

    code with alphanumeric strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "fmt
    -0.07
    ")
↵
↵
    -0.07
     Plaint
    -0.07
     тип
    -0.06
     nên
    -0.06
    UIColor
    -0.06
     akce
    -0.06
    _relu
    -0.06
    '
↵
    -0.06
    jících
    -0.06
    POSITIVE LOGITS
    ucht
    0.07
    essa
    0.06
    baar
    0.06
    SG
    0.06
    util
    0.06
     taxis
    0.06
    ensely
    0.06
     exceedingly
    0.06
     Mt
    0.06
    SUMER
    0.06
    Act Density 0.153%

    No Known Activations