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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     signs
    -0.07
     radial
    -0.07
     enterprises
    -0.07
     assessments
    -0.06
     impacts
    -0.06
     delivered
    -0.06
     Bailey
    -0.06
     forms
    -0.06
     Horizontal
    -0.06
     images
    -0.06
    POSITIVE LOGITS
    feature
    0.08
    .asInstanceOf
    0.07
     ));
↵
    0.07
    seys
    0.07
    пр
    0.06
    opo
    0.06
    ğan
    0.06
    _/
    0.06
     analsex
    0.06
    'app
    0.06
    Act Density 0.024%

    No Known Activations