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

    Neuronpedia

    INDEX
    Explanations

    ter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jacobs
    -0.07
     концентра
    -0.07
     SUBJECT
    -0.07
    -bal
    -0.07
     Grande
    -0.06
    azz
    -0.06
    _EXTENSION
    -0.06
     MMA
    -0.06
     KW
    -0.06
    ιά
    -0.06
    POSITIVE LOGITS
    lodash
    0.08
     camel
    0.06
     Sit
    0.06
    /self
    0.06
    Maint
    0.06
    -phone
    0.06
     Symfony
    0.06
    ảo
    0.06
     rozhod
    0.06
     发
    0.06
    Act Density 0.001%

    No Known Activations