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

    Neuronpedia

    INDEX
    Explanations

    all [group/people]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ological
    0.49
    eu
    0.47
    öh
    0.41
     tutto
    0.39
    pana
    0.39
    kowej
    0.39
    什么
    0.39
    usa
    0.38
     excitement
    0.38
     இதன
    0.38
    POSITIVE LOGITS
     الذين
    0.61
     who
    0.60
     ktorí
    0.54
     concerned
    0.53
     যারা
    0.53
     którzy
    0.53
     cowboys
    0.49
     kteří
    0.47
     hackers
    0.47
     bloggers
    0.47
    Act Density 0.007%

    No Known Activations