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

    Neuronpedia

    INDEX
    Explanations

    because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raining
    -0.07
     Raise
    -0.07
    気が
    -0.06
    Vs
    -0.06
    hea
    -0.06
    Reality
    -0.06
    908
    -0.06
    Called
    -0.06
    Reporting
    -0.06
    Os
    -0.06
    POSITIVE LOGITS
    inho
    0.07
    .В
    0.07
    (avg
    0.06
     mappings
    0.06
     Scheduler
    0.06
    product
    0.06
    emm
    0.06
    .cart
    0.06
    )[:
    0.06
     Predictor
    0.06
    Act Density 0.012%

    No Known Activations