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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कु�
    -0.08
     suitable
    -0.07
     Льв
    -0.07
    准确
    -0.07
    FFFFFFFF
    -0.07
     Indianapolis
    -0.07
     ಆಸ
    -0.07
     δ
    -0.07
     म्हणून
    -0.07
    iep
    -0.07
    POSITIVE LOGITS
     else's
    0.10
     person's
    0.09
     oppression
    0.09
     determinada
    0.09
     someone's
    0.09
     donnée
    0.08
     adi
    0.08
     Douglas
    0.08
     schein
    0.08
     vile
    0.07
    Act Density 0.043%

    No Known Activations