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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROUP
    -0.08
    uard
    -0.07
    enerator
    -0.07
    enerating
    -0.07
    leich
    -0.07
    overn
    -0.07
    تمع
    -0.07
    uide
    -0.07
     Ideas
    -0.07
    αλλ
    -0.07
    POSITIVE LOGITS
     GA
    0.11
     G
    0.11
     Gomez
    0.11
     GG
    0.11
     Gor
    0.10
     GC
    0.10
     gaz
    0.10
    G
    0.10
     Gill
    0.10
     Glo
    0.10
    Act Density 1.644%

    No Known Activations