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

    Neuronpedia

    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distinct
    -0.07
    _enqueue
    -0.06
    cete
    -0.06
     actionPerformed
    -0.06
    distinct
    -0.06
    _Parameter
    -0.06
    elivery
    -0.06
    ould
    -0.06
    meyi
    -0.06
     tired
    -0.06
    POSITIVE LOGITS
     ab
    0.24
    -ab
    0.12
    ab
    0.10
     Ab
    0.10
    Ab
    0.08
    .Ab
    0.08
    _AB
    0.07
    AB
    0.07
     AB
    0.07
    etting
    0.07
    Act Density 0.015%

    No Known Activations