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

    Neuronpedia

    INDEX
    Explanations

    developer mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Estimate
    -0.08
    _LOCK
    -0.08
    Transfer
    -0.07
     Estimate
    -0.07
    由
    -0.07
    ブル
    -0.07
    Converter
    -0.07
    :y
    -0.07
    Transmission
    -0.07
     transfer
    -0.07
    POSITIVE LOGITS
     unrestricted
    0.10
     knowingly
    0.09
    .Manifest
    0.09
     allegedly
    0.09
     соблюдать
    0.08
     говорится
    0.08
     দাবি
    0.08
     unstoppable
    0.08
     restrained
    0.08
     manifest
    0.08
    Act Density 0.009%

    No Known Activations