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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     principales
    -0.08
    貌
    -0.07
     obstruction
    -0.06
    (sys
    -0.06
    ^^
    -0.06
    films
    -0.06
    mitters
    -0.06
     readers
    -0.06
    ys
    -0.06
    地区
    -0.06
    POSITIVE LOGITS
    _ABS
    0.07
     благод
    0.07
     sprawling
    0.06
     Pou
    0.06
     bất
    0.06
     newRow
    0.06
     추
    0.06
     Κα
    0.06
    _phi
    0.06
     Reactive
    0.06
    Act Density 0.090%

    No Known Activations