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

    Neuronpedia

    INDEX
    Explanations

    noble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frightened
    -0.08
     mañana
    -0.08
    桐
    -0.07
     disbelief
    -0.07
    _particles
    -0.07
     saga
    -0.07
     Era
    -0.07
    extern
    -0.07
     fear
    -0.07
     feeling
    -0.07
    POSITIVE LOGITS
     noble
    0.15
     Noble
    0.14
     Nob
    0.11
     nob
    0.10
    nob
    0.09
    oble
    0.08
    (number
    0.08
     Jeb
    0.07
     lofty
    0.07
    ole
    0.07
    Act Density 0.002%

    No Known Activations