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

    Neuronpedia

    INDEX
    Explanations

    sodium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dla
    -0.06
    gos
    -0.06
    .lon
    -0.06
    /sweetalert
    -0.06
    …ط
    -0.06
    ках
    -0.06
    .concat
    -0.06
     поск
    -0.06
    .band
    -0.06
    ことを
    -0.06
    POSITIVE LOGITS
    olders
    0.07
    놓
    0.07
     associates
    0.06
    ::↵↵
    0.06
     wrongdoing
    0.06
    .',
↵
    0.06
     Kirby
    0.06
    .vue
    0.06
    '],['
    0.06
     법
    0.06
    Act Density 0.005%

    No Known Activations