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

    Neuronpedia

    INDEX
    Explanations

    excessive usage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    תקבל
    -0.07
    rud
    -0.07
    っていく
    -0.07
     которых
    -0.06
    .onChange
    -0.06
     invoice
    -0.06
     plaza
    -0.06
     Urdu
    -0.06
    壯
    -0.06
    (ext
    -0.06
    POSITIVE LOGITS
     meticulous
    0.07
     Dani
    0.07
    -m
    0.07
     Pixels
    0.07
     keynote
    0.06
    -f
    0.06
     Komm
    0.06
    -spe
    0.06
    Been
    0.06
    运气
    0.06
    Act Density 0.177%

    No Known Activations