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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     báo
    -0.08
     вій
    -0.07
    -loader
    -0.07
     "></
    -0.07
     달
    -0.07
     billionaire
    -0.07
    avir
    -0.06
    -orange
    -0.06
     fictional
    -0.06
    azen
    -0.06
    POSITIVE LOGITS
    渡
    0.06
     khung
    0.06
    مح
    0.06
     hexatrigesimal
    0.06
     (↵
    0.06
     Uh
    0.06
    .eval
    0.06
    Doing
    0.06
    _MISS
    0.06
     torino
    0.06
    Act Density 0.000%

    No Known Activations