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

    Neuronpedia

    INDEX
    Explanations

    stop words punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "D
    -0.08
    iry
    -0.08
    estr
    -0.07
    Default
    -0.07
    .Ad
    -0.07
     Bennett
    -0.06
    Cri
    -0.06
    ivol
    -0.06
    iyel
    -0.06
     Municipal
    -0.06
    POSITIVE LOGITS
     بسی
    0.06
    intendo
    0.06
    trag
    0.06
     fourteen
    0.06
    θεση
    0.06
     현대
    0.06
    ipheral
    0.06
    lys
    0.06
     sứ
    0.06
    prevent
    0.06
    Act Density 0.000%

    No Known Activations