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

    Neuronpedia

    INDEX
    Explanations

    To help me tailor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     booth
    0.74
     concret
    0.69
    Concrete
    0.68
     setCurrent
    0.65
     appalling
    0.64
     terrible
    0.64
    setIcon
    0.63
     booths
    0.63
     dangerous
    0.62
    ⵉ
    0.62
    POSITIVE LOGITS
    Option
    0.92
     Notes
    0.91
     Option
    0.89
     Choice
    0.89
    Notes
    0.87
    Choice
    0.87
     choice
    0.86
    Key
    0.85
     Which
    0.84
     Considerations
    0.84
    Act Density 0.427%

    No Known Activations