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

    Neuronpedia

    INDEX
    Explanations

    "signed" or "based" or "commitment"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yn
    0.44
    ش
    0.43
    CK
    0.42
    //
    0.42
    خ
    0.42
    il
    0.41
    AH
    0.41
    どんな
    0.41
     prazer
    0.41
    ν
    0.41
    POSITIVE LOGITS
     ბ
    0.47
     വൈറ
    0.46
     Ně
    0.45
    书城
    0.45
     Pharmacology
    0.44
    䚺
    0.44
    衤
    0.44
     Quận
    0.43
    ėje
    0.43
     Discipline
    0.43
    Act Density 0.003%

    No Known Activations