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

    Neuronpedia

    INDEX
    Explanations

    ports, gaps, specific, message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कॉम
    0.50
     NOI
    0.48
     hydros
    0.48
     comet
    0.46
     Broward
    0.46
    锜
    0.45
    చారం
    0.44
    頔
    0.44
    зино
    0.43
     Comet
    0.43
    POSITIVE LOGITS
    س
    0.54
    />
    0.52
    TR
    0.49
    的产品
    0.47
     仕事
    0.47
    Τ
    0.44
    ile
    0.43
     Existem
    0.43
    ˒
    0.43
    ಹಿ
    0.42
    Act Density 0.000%

    No Known Activations