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

    Neuronpedia

    INDEX
    Explanations

    power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    massage
    -0.07
    adero
    -0.07
     debates
    -0.07
    zelf
    -0.07
    leanor
    -0.06
    číta
    -0.06
    alert
    -0.06
     grated
    -0.06
     Eleanor
    -0.06
     NavBar
    -0.06
    POSITIVE LOGITS
     powers
    0.08
     Powers
    0.08
    cluir
    0.07
     supers
    0.06
    _counter
    0.06
     logfile
    0.06
     /************************************************************************
    0.06
     कर
    0.06
     конферен
    0.06
    identifier
    0.06
    Act Density 0.009%

    No Known Activations