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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Variable
    -0.07
     OPTIONAL
    -0.06
    esy
    -0.06
     received
    -0.06
     взгляд
    -0.06
    ishly
    -0.06
     propos
    -0.06
    -AA
    -0.06
    49
    -0.06
    urry
    -0.06
    POSITIVE LOGITS
    _mo
    0.07
    $select
    0.06
    $↵
    0.06
     Trom
    0.06
     SPE
    0.06
     oran
    0.06
     hlas
    0.06
    군요
    0.06
     Brand
    0.06
    علام
    0.06
    Act Density 0.126%

    No Known Activations