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

    Neuronpedia

    INDEX
    Explanations

    FILE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hann
    -0.07
    Orth
    -0.07
    ѕ
    -0.07
    这家
    -0.07
    browse
    -0.07
     thuốc
    -0.07
    Fuse
    -0.07
     evade
    -0.07
    ietet
    -0.06
    配方
    -0.06
    POSITIVE LOGITS
    Black
    0.07
     tłumacz
    0.07
     supremacist
    0.07
    Gtk
    0.07
     linestyle
    0.07
    🍘
    0.06
     Buenos
    0.06
     Black
    0.06
     exchange
    0.06
    鸪
    0.06
    Act Density 0.001%

    No Known Activations