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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FI
    -0.07
    盒
    -0.07
    iris
    -0.07
    palette
    -0.06
     closures
    -0.06
     pesticide
    -0.06
    一人
    -0.06
    _sheet
    -0.06
     stirred
    -0.06
    _f
    -0.06
    POSITIVE LOGITS
    問題
    0.08
    TagName
    0.07
     Bayern
    0.07
    σκευ
    0.06
    Adv
    0.06
    viewer
    0.06
    xEC
    0.06
    μάτων
    0.06
    ेण
    0.06
    _gp
    0.06
    Act Density 0.028%

    No Known Activations