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

    Neuronpedia

    INDEX
    Explanations

    action and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    crystalline
    0.39
    峻
    0.39
     basalt
    0.38
     Basil
    0.37
     Jenny
    0.37
    ership
    0.36
    quinoline
    0.36
    Cabe
    0.36
     Haga
    0.35
     mün
    0.35
    POSITIVE LOGITS
     payload
    0.85
     parameters
    0.79
    payload
    0.75
     Arguments
    0.73
     Parameters
    0.71
     Payload
    0.71
    Payload
    0.70
     argument
    0.69
     content
    0.68
     arguments
    0.68
    Act Density 0.020%

    No Known Activations