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

    Neuronpedia

    INDEX
    Explanations

    command line flags and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amounts
    0.50
     Mushrooms
    0.50
     Mixtures
    0.49
     Galaxies
    0.47
     Биз
    0.47
     Viruses
    0.46
     Managers
    0.46
    DTDs
    0.46
     Elektrokh
    0.46
    aguars
    0.46
    POSITIVE LOGITS
    <0xE3>
    0.46
     is
    0.44
     check
    0.44
     attention
    0.44
     match
    0.41
     help
    0.40
    <0xC2>
    0.40
     response
    0.38
     guess
    0.38
     order
    0.37
    Act Density 0.032%

    No Known Activations