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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecz
    -0.06
    argas
    -0.06
    子的
    -0.06
     Александр
    -0.06
    tube
    -0.06
     cuisine
    -0.06
    운
    -0.06
    amma
    -0.06
     Hasan
    -0.05
    glyph
    -0.05
    POSITIVE LOGITS
    licate
    0.07
     Victory
    0.07
    .Relative
    0.07
    енный
    0.07
    licts
    0.06
    .ts
    0.06
    (TAG
    0.06
    _cell
    0.06
    ltk
    0.06
    ognitive
    0.06
    Act Density 0.150%

    No Known Activations