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

    Neuronpedia

    INDEX
    Explanations

    difficult terrain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roll
    -0.07
    属于
    -0.07
    سمة
    -0.07
     declare
    -0.07
    iples
    -0.07
     Dien
    -0.07
     cares
    -0.07
     correction
    -0.06
     Removed
    -0.06
     землі
    -0.06
    POSITIVE LOGITS
     Мин
    0.07
    -not
    0.06
    ouv
    0.06
     csrf
    0.06
     перем
    0.06
    층
    0.06
    ži
    0.06
     specs
    0.06
     Doğ
    0.06
    aft
    0.06
    Act Density 0.085%

    No Known Activations