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

    Neuronpedia

    INDEX
    Explanations

    tables and markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]
    0.59
    h
    0.54
    v
    0.49
    )
    0.49
     Rod
    0.48
    }
    0.48
     Purdue
    0.48
     Commonwealth
    0.47
    leton
    0.47
    1
    0.47
    POSITIVE LOGITS
    ЛА
    0.56
     établ
    0.56
    tı
    0.54
    唵
    0.54
    tweets
    0.54
     зеле
    0.54
     électron
    0.54
     étale
    0.52
    𝖐
    0.52
    BANG
    0.52
    Act Density 0.000%

    No Known Activations