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

    Neuronpedia

    INDEX
    Explanations

    chemistry and physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cold
    -0.07
     snug
    -0.06
     Yen
    -0.06
     transformer
    -0.06
     Nug
    -0.06
    .art
    -0.06
     piece
    -0.06
     anger
    -0.06
     Intent
    -0.06
     oversight
    -0.06
    POSITIVE LOGITS
     &&↵
    0.07
    成為
    0.07
    )
↵
↵
↵
    0.07
    ]↵↵
    0.06
     Alman
    0.06
    "]↵↵
    0.06
     البلد
    0.06
    _();↵
    0.06
    osci
    0.06
     спросил
    0.06
    Act Density 0.012%

    No Known Activations