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

    Neuronpedia

    INDEX
    Explanations

    verse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glitter
    -0.08
     Egg
    -0.07
     Destruction
    -0.07
     Kahn
    -0.07
    dı
    -0.06
     either
    -0.06
    ilated
    -0.06
    OA
    -0.06
     Dirt
    -0.06
    Dict
    -0.06
    POSITIVE LOGITS
    verse
    0.10
    VERSE
    0.07
     Test
    0.07
    620
    0.06
     Passive
    0.06
    tiler
    0.06
    stop
    0.06
    �
    0.06
    Resolve
    0.06
     excessive
    0.06
    Act Density 0.002%

    No Known Activations