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

    Neuronpedia

    INDEX
    Explanations

    recess

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kindly
    -0.07
     photoc
    -0.06
    788
    -0.06
     Mostly
    -0.06
    олаг
    -0.06
     kidding
    -0.06
     juste
    -0.05
    League
    -0.05
    “It
    -0.05
    pon
    -0.05
    POSITIVE LOGITS
    (Logger
    0.07
     Annex
    0.07
     vocalist
    0.07
    _acc
    0.07
     كرة
    0.07
     vortex
    0.06
    pace
    0.06
     IService
    0.06
     гра
    0.06
    ीश
    0.06
    Act Density 0.001%

    No Known Activations