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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drunken
    -0.06
    .cycle
    -0.06
    opathy
    -0.06
    Saturday
    -0.06
    .NUM
    -0.06
     لف
    -0.06
    408
    -0.06
    ประมาณ
    -0.06
    '}}>↵
    -0.06
    resizing
    -0.06
    POSITIVE LOGITS
     기능
    0.08
     Department
    0.07
    Delegate
    0.07
    (File
    0.07
     Checkout
    0.06
     features
    0.06
     Shades
    0.06
     Feature
    0.06
     ability
    0.06
     Glass
    0.06
    Act Density 0.062%

    No Known Activations