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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ₨
    -0.07
    ڑ
    -0.07
    (Cs
    -0.07
    陲
    -0.07
    색
    -0.07
    쯧
    -0.07
    ful
    -0.06
    ailand
    -0.06
     처음
    -0.06
    山西省
    -0.06
    POSITIVE LOGITS
     Freak
    0.07
    liquid
    0.07
    两人
    0.07
    -ground
    0.07
     workings
    0.07
    ☖
    0.07
    سحب
    0.07
    stop
    0.07
    aised
    0.07
     entrenched
    0.07
    Act Density 0.001%

    No Known Activations