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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ais
    -0.07
     Urb
    -0.07
    "},
    -0.06
    웅
    -0.06
     Empty
    -0.06
    ..
    -0.06
    osh
    -0.06
    通信
    -0.06
    Raw
    -0.06
    原
    -0.06
    POSITIVE LOGITS
    催
    0.06
    HAND
    0.06
     DOCUMENT
    0.06
     profes
    0.06
    Allowed
    0.06
     misc
    0.06
    =[]
↵
    0.06
    /******************************************************************************↵
    0.06
    theValue
    0.06
    ?=.*
    0.06
    Act Density 0.040%

    No Known Activations