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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tires
    -0.08
     Attorneys
    -0.08
    -ke
    -0.08
     Kecamatan
    -0.08
     Kle
    -0.08
     moz
    -0.08
    ениями
    -0.07
     ke
    -0.07
     hare
    -0.07
    -being
    -0.07
    POSITIVE LOGITS
    规格
    0.11
     paperback
    0.11
     вариант
    0.10
    版
    0.10
     verkrijgbaar
    0.10
     wers
    0.10
    版本
    0.09
     formats
    0.09
     संस्करण
    0.09
     versions
    0.09
    Act Density 0.026%

    No Known Activations