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

    Neuronpedia

    INDEX
    Explanations

    API

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Buzz
    -0.08
     Buzz
    -0.08
    dev
    -0.08
    bf
    -0.08
     Libert
    -0.07
     অধ
    -0.07
     Indie
    -0.07
     ganzen
    -0.07
    ¥
    -0.07
     enriquec
    -0.07
    POSITIVE LOGITS
     المث
    0.08
    剤
    0.08
     distinctions
    0.07
     م
    0.07
     दशक
    0.07
     tooth
    0.07
     odpr
    0.07
    �
    0.07
     sling
    0.07
     intertwined
    0.07
    Act Density 0.001%

    No Known Activations