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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cigars
    -0.06
    ーナ
    -0.06
     Stockholm
    -0.06
    Modules
    -0.06
    folk
    -0.06
    ϊκ
    -0.06
    airobi
    -0.06
     Gingrich
    -0.06
    located
    -0.06
     Ú
    -0.06
    POSITIVE LOGITS
     Entities
    0.07
    .wr
    0.07
     nä
    0.06
     Kw
    0.06
    asında
    0.06
    _w
    0.06
     Butt
    0.06
     PQ
    0.06
     stew
    0.06
    érience
    0.06
    Act Density 0.079%

    No Known Activations