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

    Neuronpedia

    INDEX
    Explanations

    code functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اة
    -0.08
     assembly
    -0.07
     också
    -0.07
    ully
    -0.07
    十三
    -0.07
    ними
    -0.07
    于
    -0.06
    ाँ
    -0.06
    ro
    -0.06
     Santiago
    -0.06
    POSITIVE LOGITS
     indexer
    0.07
     RIP
    0.06
     เคร
    0.06
    .hours
    0.06
    _COLL
    0.06
    idos
    0.06
    -access
    0.06
     gums
    0.06
     Coch
    0.06
     كم
    0.06
    Act Density 0.286%

    No Known Activations