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

    Neuronpedia

    INDEX
    Explanations

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OAc
    0.49
    SFR
    0.45
    LIN
    0.45
    O
    0.45
    Instead
    0.44
    দ্রোহ
    0.44
    Sch
    0.42
    AW
    0.42
    POLY
    0.42
    quota
    0.41
    POSITIVE LOGITS
     g
    0.50
     submar
    0.48
     GTS
    0.48
     post
    0.47
     muse
    0.45
     HSV
    0.45
     DTS
    0.44
     HT
    0.44
     dipl
    0.44
     serm
    0.44
    Act Density 0.002%

    No Known Activations