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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Level
    -0.08
    -Length
    -0.07
     PrintWriter
    -0.07
    Bitmap
    -0.07
    芗
    -0.07
    _Record
    -0.06
    rchive
    -0.06
    NK
    -0.06
    .setTextColor
    -0.06
    莪
    -0.06
    POSITIVE LOGITS
     conference
    0.07
    _parameters
    0.07
    ||↵
    0.07
    VALID
    0.07
     mag
    0.07
     TEST
    0.07
     unsure
    0.07
     עולה
    0.07
    かける
    0.07
    כנס
    0.07
    Act Density 0.006%

    No Known Activations