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

    Neuronpedia

    INDEX
    Explanations

    strong belief in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    து
    1.48
     worries
    1.32
     infamous
    1.30
     بحث
    1.26
    ar
    1.26
    場合
    1.25
    越南
    1.24
    ского
    1.23
    𝐄
    1.22
    ahre
    1.22
    POSITIVE LOGITS
     firmly
    1.70
     strongly
    1.59
     wholeheartedly
    1.53
    ជាក់
    1.46
     steadfast
    1.40
    inch
    1.39
     stroj
    1.38
     fullName
    1.35
     puncak
    1.32
    ievable
    1.32
    Act Density 0.035%

    No Known Activations