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

    Neuronpedia

    INDEX
    Explanations

    Code/Debugging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .copy
    -0.07
    私立
    -0.07
    _combine
    -0.07
     misunderstand
    -0.07
    知道了
    -0.07
     functor
    -0.07
     CSI
    -0.06
     keto
    -0.06
     وهناك
    -0.06
    咎
    -0.06
    POSITIVE LOGITS
    illos
    0.07
    حظ
    0.07
     cin
    0.07
     reaches
    0.06
     roll
    0.06
    loading
    0.06
     mix
    0.06
     Balls
    0.06
     GridLayout
    0.06
     looping
    0.06
    Act Density 0.004%

    No Known Activations