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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ben
    -0.07
    Audio
    -0.07
     Καρ
    -0.06
     их
    -0.06
    257
    -0.06
     Walt
    -0.06
     Pen
    -0.06
    玉
    -0.06
     banana
    -0.06
    heard
    -0.06
    POSITIVE LOGITS
    omanip
    0.08
    .netty
    0.07
    إ
    0.07
    rob
    0.06
    .AddModelError
    0.06
    .arange
    0.06
     fucks
    0.06
     getSupportActionBar
    0.06
    (update
    0.06
    iomanip
    0.06
    Act Density 0.263%

    No Known Activations