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

    Neuronpedia

    INDEX
    Explanations

    role definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    resistance
    0.67
     경우는
    0.59
    earnings
    0.56
     সুবি
    0.56
     ಪ್ರಯೋಜನ
    0.56
    assertion
    0.55
    िवा
    0.55
    testAvg
    0.55
    u
    0.55
     Klicken
    0.54
    POSITIVE LOGITS
     be
    0.65
    कर्ताओं
    0.55
     S
    0.54
    出
    0.54
    后
    0.54
     N
    0.53
     O
    0.53
    тся
    0.52
     druk
    0.52
    вание
    0.51
    Act Density 0.006%

    No Known Activations