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

    Neuronpedia

    INDEX
    Explanations

    malicious activities and attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лата
    0.50
     IMPLIED
    0.49
     называ
    0.47
    اونلو
    0.46
    ᠶ
    0.46
    seign
    0.46
    ні
    0.46
     pandémie
    0.46
    IVERY
    0.45
    ูณ
    0.45
    POSITIVE LOGITS
     จน
    0.49
     continúa
    0.46
    ota
    0.45
    ce
    0.42
     Lok
    0.42
    ate
    0.41
    te
    0.40
     continua
    0.40
    sta
    0.40
     toward
    0.40
    Act Density 0.007%

    No Known Activations