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

    Neuronpedia

    INDEX
    Explanations

    programming range function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '*
    0.67
    পাট
    0.65
    *"
    0.65
    ৃত
    0.64
    jamin
    0.64
    ({'
    0.63
    neq
    0.62
     ব্যবস
    0.62
    டுக
    0.62
    啷
    0.62
    POSITIVE LOGITS
     comenzar
    0.85
     બીજી
    0.85
     pacific
    0.82
     blog
    0.78
     दुसरी
    0.78
    臨時
    0.76
     دوسری
    0.75
    從
    0.74
    下載
    0.73
     приез
    0.72
    Act Density 0.037%

    No Known Activations