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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rep
    -0.07
    [start
    -0.06
     ={
    -0.06
     valu
    -0.06
    .onSubmit
    -0.06
    controller
    -0.06
    eec
    -0.06
    цин
    -0.06
     powerhouse
    -0.06
     dropout
    -0.06
    POSITIVE LOGITS
     και
    0.07
     improvements
    0.07
     Appro
    0.07
    住宅
    0.06
    .forRoot
    0.06
    енной
    0.06
     Shotgun
    0.06
    _armor
    0.06
     Hopefully
    0.06
    ifest
    0.06
    Act Density 0.002%

    No Known Activations