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

    Neuronpedia

    INDEX
    Explanations

    list items and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     baru
    0.39
     Glad
    0.37
     теркә
    0.37
    ピソード
    0.37
     Oil
    0.37
     Threat
    0.37
     Grant
    0.36
    ilina
    0.36
     Concrete
    0.35
     finalist
    0.35
    POSITIVE LOGITS
    らの
    0.40
    PTR
    0.40
    cyclic
    0.38
    랏
    0.37
    Aaj
    0.37
     সহিত
    0.37
    ртом
    0.37
    şey
    0.36
    Alf
    0.36
    medieval
    0.36
    Act Density 0.000%

    No Known Activations