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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ordered
    -0.06
    -io
    -0.06
    saved
    -0.06
     pathways
    -0.06
     birthdays
    -0.06
    birthday
    -0.06
    /routes
    -0.06
     candidates
    -0.06
    ervals
    -0.06
     sang
    -0.05
    POSITIVE LOGITS
    ]{
    0.07
     marginRight
    0.07
    elor
    0.07
    /qt
    0.07
    ánt
    0.06
    _FRONT
    0.06
     Ihre
    0.06
    .MiddleLeft
    0.06
    že
    0.06
     Approx
    0.06
    Act Density 0.066%

    No Known Activations