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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scaling
    -0.06
     buyer
    -0.06
    ptr
    -0.06
    _TESTS
    -0.06
    yy
    -0.06
     prosecuting
    -0.06
     disjoint
    -0.06
     prisoner
    -0.06
     Substance
    -0.06
     descriptor
    -0.06
    POSITIVE LOGITS
     Taco
    0.07
    kem
    0.07
    ıyoruz
    0.06
    ertainment
    0.06
     Gina
    0.06
     Provid
    0.06
     athletic
    0.06
     GCC
    0.06
     hi
    0.06
     flatt
    0.06
    Act Density 0.003%

    No Known Activations