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

    Neuronpedia

    INDEX
    Explanations

    themselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reach
    -0.06
     Those
    -0.06
     �
    -0.06
     sav
    -0.06
     margin
    -0.06
    Px
    -0.06
    メ
    -0.06
    Υ
    -0.06
     ConfigurationManager
    -0.06
    Lİ
    -0.06
    POSITIVE LOGITS
     جمله
    0.07
    ΗΜΑ
    0.07
    χαν
    0.07
    ake
    0.06
    normally
    0.06
    etal
    0.06
    oval
    0.06
    atty
    0.06
    oky
    0.06
    /about
    0.06
    Act Density 0.000%

    No Known Activations