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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grille
    -0.06
    े-
    -0.06
     Juli
    -0.06
     پ
    -0.06
    Daily
    -0.06
    ungkin
    -0.06
    eyn
    -0.06
    	il
    -0.06
    TL
    -0.06
    PrototypeOf
    -0.06
    POSITIVE LOGITS
     InkWell
    0.07
    lev
    0.07
    摘要
    0.06
     discrete
    0.06
    Fee
    0.06
     urban
    0.06
    ernity
    0.06
     Drama
    0.06
    -Length
    0.06
     Stable
    0.06
    Act Density 0.008%

    No Known Activations