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
    기업
    -0.08
    =log
    -0.08
    資
    -0.08
    _READONLY
    -0.07
     còn
    -0.07
    术后
    -0.07
     events
    -0.07
    .Chat
    -0.07
     franch
    -0.07
     Ish
    -0.07
    POSITIVE LOGITS
    emple
    0.07
     Piano
    0.07
    部位
    0.07
    ByKey
    0.06
    坬
    0.06
    OI
    0.06
    تعب
    0.06
    cedure
    0.06
    pee
    0.06
     Howell
    0.06
    Act Density 0.000%

    No Known Activations