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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hw
    -0.08
    もっと
    -0.07
    vesting
    -0.07
    Expense
    -0.07
     hingegen
    -0.07
    -Aus
    -0.07
     footsteps
    -0.07
     esos
    -0.07
     expenses
    -0.07
    adis
    -0.07
    POSITIVE LOGITS
     смог
    0.09
     достига
    0.09
     conseguiu
    0.08
     بتوان
    0.08
     получилось
    0.08
     fud
    0.08
     podido
    0.08
     Ż
    0.08
     tornam
    0.08
     longevity
    0.08
    Act Density 0.122%

    No Known Activations