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

    Neuronpedia

    INDEX
    Explanations

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    psilon
    0.37
     Exec
    0.37
     jira
    0.36
    Wire
    0.36
     None
    0.35
     squiggle
    0.35
    jira
    0.35
     nenhuma
    0.34
    HCM
    0.34
    螓
    0.34
    POSITIVE LOGITS
     ①
    0.43
    াপন্ন
    0.39
     нес
    0.39
    上面
    0.37
     vape
    0.36
     सदा
    0.36
     जब
    0.36
     попу
    0.36
    Vocabulary
    0.35
     كلمات
    0.35
    Act Density 0.009%

    No Known Activations