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

    Neuronpedia

    INDEX
    Explanations

    Q&A forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     may
    -0.07
    Attrs
    -0.07
    ます
    -0.07
     want
    -0.07
    яг
    -0.06
    )));
↵
    -0.06
     differ
    -0.06
    чає
    -0.06
     ZERO
    -0.06
     LAN
    -0.06
    POSITIVE LOGITS
     único
    0.06
    0.06
    0.06
     annoyance
    0.06
     Prec
    0.06
    agento
    0.06
    enumerate
    0.06
    fortune
    0.06
    IGNORE
    0.06
    αρά
    0.06
    Act Density 0.322%

    No Known Activations