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

    Neuronpedia

    INDEX
    Explanations

    prime numbers after 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Runs
    0.50
     Enzymes
    0.50
    (...
    0.49
     Oper
    0.46
     Sympt
    0.45
     andrew
    0.45
     Chain
    0.44
     Consecutive
    0.44
     During
    0.43
     Enzyme
    0.43
    POSITIVE LOGITS
     “‘
    0.49
     socalled
    0.48
    こうした
    0.48
     troubled
    0.46
    ].”
    0.45
     hazardous
    0.43
     extraordinarily
    0.43
     perilous
    0.42
     ‘‘
    0.42
    citizen
    0.41
    Act Density 0.000%

    No Known Activations