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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     организма
    -0.08
     kartu
    -0.08
     karta
    -0.08
     카
    -0.08
    (Constant
    -0.08
     kare
    -0.08
    ката
    -0.08
    Mixin
    -0.08
    妈妈
    -0.07
    Constant
    -0.07
    POSITIVE LOGITS
     отношении
    0.10
     بشأن
    0.10
     честь
    0.09
     banyere
    0.09
     behalf
    0.09
     asuntos
    0.09
     accordance
    0.09
     להש
    0.08
     honour
    0.08
    案件
    0.08
    Act Density 0.062%

    No Known Activations