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

    Neuronpedia

    INDEX
    Explanations

    in location or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    str
    0.35
        
    0.33
    n
    0.33
    ↵
    0.31
    im
    0.31
    chromosome
    0.31
    enhancing
    0.31
    defined
    0.31
    few
    0.31
    sense
    0.31
    POSITIVE LOGITS
     captivity
    0.43
     pajamas
    0.43
     perpetuity
    0.42
     triplicate
    0.41
     bunkers
    0.41
     spades
    0.40
     paradise
    0.39
     hopes
    0.39
     town
    0.38
     Amerika
    0.38
    Act Density 0.102%

    No Known Activations