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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theatrical
    -0.07
     Efficiency
    -0.07
     Has
    -0.06
    au
    -0.06
    DBus
    -0.06
    ane
    -0.06
    ylv
    -0.06
     pasa
    -0.06
     ((
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     spinner
    0.07
    VERTISE
    0.06
     attorneys
    0.06
    aney
    0.06
    NASA
    0.06
    $model
    0.06
    这是
    0.06
     kontrol
    0.06
     patrons
    0.06
     tanggal
    0.06
    Act Density 0.026%

    No Known Activations