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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ị
    -0.07
     leo
    -0.07
     tud
    -0.07
     ember
    -0.07
     نفسه
    -0.07
    remain
    -0.06
    attendance
    -0.06
    обыти
    -0.06
    stanbul
    -0.06
    ]>=
    -0.06
    POSITIVE LOGITS
    .UI
    0.07
    Days
    0.07
    -With
    0.06
    frey
    0.06
     Cycle
    0.06
    =Value
    0.06
    تور
    0.06
     entitled
    0.06
    iş
    0.06
     consisted
    0.06
    Act Density 0.000%

    No Known Activations