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

    Neuronpedia

    INDEX
    Explanations

    differentcontexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tracking
    0.55
    ゼロ
    0.46
    病人
    0.43
    archive
    0.43
    anganan
    0.43
    的服务
    0.43
    跟踪
    0.42
    pointing
    0.42
    7
    0.42
     اڈوں
    0.42
    POSITIVE LOGITS
     anderes
    0.49
     oiseaux
    0.46
     మె
    0.46
     export
    0.44
    !()
    0.44
     tornado
    0.44
     सोने
    0.43
     enfant
    0.42
     дет
    0.42
     така
    0.42
    Act Density 0.004%

    No Known Activations