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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _perf
    -0.07
    (Server
    -0.06
     آخرین
    -0.06
     düzenli
    -0.06
    [block
    -0.06
    _PRED
    -0.06
    rompt
    -0.06
     ROOM
    -0.06
     тщ
    -0.06
     지난
    -0.06
    POSITIVE LOGITS
     employer
    0.07
     harass
    0.06
    ("")]↵
    0.06
     Pope
    0.06
    *****/↵
    0.06
     income
    0.06
    olah
    0.06
    invoke
    0.06
     applicant
    0.06
     işte
    0.06
    Act Density 0.041%

    No Known Activations