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

    Neuronpedia

    INDEX
    Explanations

    am, apologizing, still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کروچ
    0.46
    াচার্য
    0.40
     عرص
    0.39
     arqué
    0.38
     extrap
    0.38
     छुट्ट
    0.38
    octrl
    0.37
    frast
    0.37
     fears
    0.37
     گئیں
    0.37
    POSITIVE LOGITS
    ⲟ
    0.66
    ᥙ
    0.66
    ᧐
    0.66
    ｅ
    0.63
    ߋ
    0.63
    ԝ
    0.60
    Ⲟ
    0.60
     һ
    0.58
    ѡ
    0.58
    ɑ
    0.58
    Act Density 0.001%

    No Known Activations