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

    Neuronpedia

    INDEX
    Explanations

    code and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     第三
    -0.07
    [opt
    -0.07
     основном
    -0.06
     εί
    -0.06
    ocket
    -0.06
    _expr
    -0.06
     clot
    -0.06
    elerine
    -0.06
     zejména
    -0.06
     hastily
    -0.06
    POSITIVE LOGITS
    ٢
    0.07
     confuse
    0.07
     eup
    0.06
     सब
    0.06
     Elli
    0.06
    _changed
    0.06
     superficial
    0.06
    Porn
    0.06
    淡
    0.06
    dbg
    0.06
    Act Density 0.156%

    No Known Activations