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

    Neuronpedia

    INDEX
    Explanations

    code directories

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ../
    0.88
     ./
    0.86
     SRC
    0.79
    Src
    0.77
    SRC
    0.71
     dst
    0.71
    ~/
    0.71
     srcs
    0.70
     "./
    0.69
    ../
    0.69
    POSITIVE LOGITS
    bring
    0.54
    Bring
    0.50
     தலைமை
    0.50
     cư
    0.50
    リオ
    0.50
     bawa
    0.50
     bring
    0.47
     Bring
    0.47
    नु
    0.47
     proč
    0.47
    Act Density 0.000%

    No Known Activations