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

    Neuronpedia

    INDEX
    Explanations

    habits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hatch
    -0.07
     FML
    -0.07
    ANGE
    -0.06
     logos
    -0.06
    ange
    -0.06
    _context
    -0.06
     touchdown
    -0.06
     Coffee
    -0.06
     meaning
    -0.06
     Soup
    -0.06
    POSITIVE LOGITS
     downstream
    0.07
    _active
    0.07
     alış
    0.06
     Send
    0.06
     Tunisia
    0.06
     setSelected
    0.06
    ledged
    0.06
    ollectors
    0.06
    aviors
    0.06
    zc
    0.06
    Act Density 0.156%

    No Known Activations