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

    Neuronpedia

    INDEX
    Explanations

    joke setups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     now
    0.85
     헤
    0.83
     ממ
    0.78
     منح
    0.77
     tér
    0.76
     전망
    0.76
     지금
    0.75
    דע
    0.75
     nyní
    0.75
    不然
    0.75
    POSITIVE LOGITS
     centrifugation
    0.93
    𝐓
    0.90
     scavenging
    0.90
    Termination
    0.81
     vaginal
    0.80
     turbocharged
    0.79
     styled
    0.79
    を使用した
    0.79
    ओ
    0.78
     کے
    0.77
    Act Density 0.027%

    No Known Activations