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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     withd
    -0.07
    елю
    -0.07
     evapor
    -0.06
     वस
    -0.06
    лет
    -0.06
    -tm
    -0.06
     Stark
    -0.06
    )'),
    -0.06
     fors
    -0.06
     uc
    -0.06
    POSITIVE LOGITS
     ballet
    0.07
    erate
    0.06
    계획
    0.06
     صنع
    0.06
    wb
    0.06
     verifying
    0.06
    该
    0.06
    _POLL
    0.06
    bill
    0.06
    .addProperty
    0.06
    Act Density 0.004%

    No Known Activations