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

    Neuronpedia

    INDEX
    Explanations

    Core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     其
    -0.07
    /TR
    -0.07
     Mez
    -0.07
    386
    -0.06
    ="?
    -0.06
    boom
    -0.06
     già
    -0.06
     lul
    -0.06
     aust
    -0.06
     Ware
    -0.06
    POSITIVE LOGITS
     vectors
    0.07
     constants
    0.07
    _sigma
    0.07
    RefPtr
    0.06
     FIXME
    0.06
     interest
    0.06
    postgresql
    0.06
     функци
    0.06
    RIES
    0.06
    協
    0.06
    Act Density 0.006%

    No Known Activations