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

    Neuronpedia

    INDEX
    Explanations

    huge amount of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.47
    venidas
    0.44
    enciales
    0.43
    kari
    0.42
    ariyati
    0.42
    ﾑ
    0.42
    קים
    0.41
     ouvertes
    0.41
    arians
    0.40
    צים
    0.40
    POSITIVE LOGITS
     Entertain
    0.46
     YOUR
    0.45
     மாய
    0.41
    漁
    0.41
     музыку
    0.40
     decât
    0.39
    Diethyl
    0.39
    音楽
    0.38
     bandage
    0.38
    YOUR
    0.38
    Act Density 0.002%

    No Known Activations