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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ric
    -0.07
     sha
    -0.07
     är
    -0.07
     TREE
    -0.06
     anv
    -0.06
     Plays
    -0.06
    _ps
    -0.06
     rename
    -0.06
     totalPrice
    -0.06
    Resizable
    -0.06
    POSITIVE LOGITS
    Pakistan
    0.07
    나
    0.06
    (thing
    0.06
    routeProvider
    0.06
    dependency
    0.06
    INTERN
    0.06
    태
    0.06
     kwargs
    0.06
     misogyn
    0.06
    .hardware
    0.06
    Act Density 0.430%

    No Known Activations