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

    Neuronpedia

    INDEX
    Explanations

    the Americas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ies
    0.52
     ropa
    0.49
    resolver
    0.45
     resolver
    0.45
    estep
    0.44
    ings
    0.43
    รรม
    0.43
    িলে
    0.43
    aj
    0.43
    瀝
    0.43
    POSITIVE LOGITS
    𝟕
    0.51
     élég
    0.51
    Beware
    0.49
     午
    0.47
    Sullivan
    0.47
    િ
    0.47
     अ
    0.46
     скоро
    0.46
     सु
    0.45
     त्रुट
    0.45
    Act Density 0.000%

    No Known Activations