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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     F
    -0.07
    interp
    -0.07
     sóc
    -0.07
    _Rem
    -0.06
    ارش
    -0.06
     Πολ
    -0.06
     RB
    -0.06
    额
    -0.06
     Arb
    -0.06
    F
    -0.06
    POSITIVE LOGITS
    اریخ
    0.07
    foundland
    0.07
     віднов
    0.07
     cannabis
    0.06
    qualified
    0.06
     Vancouver
    0.06
    .SIZE
    0.06
     successive
    0.06
    }catch
    0.06
     返回
    0.06
    Act Density 0.083%

    No Known Activations