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

    Neuronpedia

    INDEX
    Explanations

    after historical events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     regelmatig
    0.55
     صي
    0.46
     nông
    0.46
    ujen
    0.45
     নৈ
    0.44
     cang
    0.44
     badan
    0.44
    بارك
    0.44
     Rostock
    0.44
     répond
    0.43
    POSITIVE LOGITS
    ジャ
    0.43
    truth
    0.42
    gone
    0.42
    くる
    0.41
    nesses
    0.41
    ۔
    0.40
    ರಿಸಿ
    0.40
    ವಾಗಿ
    0.40
    mystery
    0.40
    dream
    0.39
    Act Density 0.000%

    No Known Activations