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

    Neuronpedia

    INDEX
    Explanations

    model numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pa
    -0.07
    ﱠ
    -0.07
     warehouses
    -0.07
     vectors
    -0.07
    סל
    -0.07
    減
    -0.07
    ὔ
    -0.07
    ʣ
    -0.07
    Spe
    -0.07
    una
    -0.07
    POSITIVE LOGITS
     lire
    0.08
     banging
    0.07
    abstract
    0.07
     obrig
    0.07
    sortBy
    0.07
    פוליטי
    0.07
    有趣
    0.07
     bcrypt
    0.07
    怎样
    0.07
    With
    0.07
    Act Density 0.062%

    No Known Activations