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
    -0.09
    rowth
    -0.09
    reatest
    -0.08
    reater
    -0.08
    uard
    -0.08
    eneration
    -0.08
    enerating
    -0.08
    117
    -0.08
    administrator
    -0.08
     tts
    -0.08
    POSITIVE LOGITS
     Gast
    0.11
     Gill
    0.10
     Gong
    0.10
    -G
    0.10
    (G
    0.10
     Gib
    0.10
    <G
    0.10
     Gat
    0.10
     Gur
    0.10
     gul
    0.10
    Act Density 0.847%

    No Known Activations