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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sense
    -0.07
     benches
    -0.07
     hatch
    -0.07
    norm
    -0.07
    柴
    -0.07
     IsActive
    -0.06
    "]}
    -0.06
     stressed
    -0.06
    CALE
    -0.06
    datable
    -0.06
    POSITIVE LOGITS
     teens
    0.06
    Não
    0.06
     pyramid
    0.06
    atrib
    0.06
     pouco
    0.06
     excess
    0.06
     exhibition
    0.06
    انون
    0.06
    quences
    0.06
    emiah
    0.06
    Act Density 0.001%

    No Known Activations