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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ride
    -0.07
     perfect
    -0.07
    <Response
    -0.06
    NG
    -0.06
     prefect
    -0.06
    เจ
    -0.06
     ride
    -0.06
     area
    -0.06
    Echo
    -0.06
     generation
    -0.06
    POSITIVE LOGITS
    flamm
    0.07
    地址
    0.07
    Scala
    0.07
    ANCED
    0.06
    composition
    0.06
    igmoid
    0.06
    VO
    0.06
    ocities
    0.06
     xmlns
    0.06
    اطل
    0.06
    Act Density 0.000%

    No Known Activations