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

    Neuronpedia

    INDEX
    Explanations

    books and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )|
    0.43
     começou
    0.42
    ک
    0.42
     Otago
    0.41
     alten
    0.41
     p
    0.40
     thyroid
    0.40
     OS
    0.40
     altri
    0.40
     enzyme
    0.39
    POSITIVE LOGITS
     〢
    0.40
    从而
    0.39
    Einstellungen
    0.38
    谚
    0.37
    neys
    0.37
    ]---
    0.37
    Butyl
    0.36
     Veranstaltungen
    0.36
    enfance
    0.36
    叁章
    0.36
    Act Density 0.002%

    No Known Activations