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
    larındaki
    -0.07
    {l
    -0.07
     exemplo
    -0.06
    iene
    -0.06
     Hoy
    -0.06
     Duy
    -0.06
    _Interface
    -0.06
    ampaign
    -0.06
    assertInstanceOf
    -0.06
    calls
    -0.06
    POSITIVE LOGITS
     smash
    0.06
    арь
    0.06
     공격
    0.06
     "}↵
    0.06
     برابر
    0.06
     invaded
    0.06
     automobile
    0.06
    енная
    0.06
     bunny
    0.06
    !.
    0.06
    Act Density 0.008%

    No Known Activations