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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نور
    -0.07
    speech
    -0.07
     جنسی
    -0.06
     ser
    -0.06
     Qur
    -0.06
    nest
    -0.06
    ッチ
    -0.06
    -floor
    -0.06
     Madagascar
    -0.06
    れる
    -0.06
    POSITIVE LOGITS
     solutions
    0.07
     uns
    0.07
     Fargo
    0.07
     dynam
    0.06
     tion
    0.06
     DMA
    0.06
    BO
    0.06
    mploy
    0.06
    ução
    0.06
    forum
    0.06
    Act Density 0.027%

    No Known Activations