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

    Neuronpedia

    INDEX
    Explanations

    code/math/random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    epad
    -0.07
     tabs
    -0.07
     Issues
    -0.07
     adrenaline
    -0.06
     Padding
    -0.06
     pads
    -0.06
     jaws
    -0.06
     mile
    -0.06
     collided
    -0.06
     Riy
    -0.06
    POSITIVE LOGITS
    "];
↵
    0.06
    ी.
    0.06
    Clone
    0.06
    iei
    0.06
    füg
    0.06
    _ten
    0.06
    (weights
    0.06
     کمک
    0.06
    žel
    0.06
     flock
    0.06
    Act Density 0.000%

    No Known Activations