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

    Neuronpedia

    INDEX
    Explanations

    at first or its core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    had
    0.82
    ال
    0.82
     putem
    0.79
    라도
    0.79
     是否
    0.79
    eous
    0.77
     का
    0.77
    ात
    0.77
    ious
    0.76
     egyéb
    0.74
    POSITIVE LOGITS
     least
    2.20
     times
    1.61
    least
    1.55
     outset
    1.51
     intervals
    1.35
    rocities
    1.33
    Least
    1.32
     night
    1.29
     dawn
    1.29
     Least
    1.25
    Act Density 0.181%

    No Known Activations