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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vari
    -0.06
     Db
    -0.06
     Killing
    -0.06
    [max
    -0.06
    ฐาน
    -0.06
     Brew
    -0.06
    iyeti
    -0.06
    397
    -0.06
    ApiModelProperty
    -0.05
    нение
    -0.05
    POSITIVE LOGITS
    motion
    0.07
     Lite
    0.07
     cà
    0.07
    measurement
    0.07
     bespoke
    0.07
     vnode
    0.07
     prevents
    0.06
    incr
    0.06
    мом
    0.06
     mắt
    0.06
    Act Density 0.146%

    No Known Activations