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

    Neuronpedia

    INDEX
    Explanations

    URLs and developer resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estím
    0.43
     Nept
    0.39
    action
    0.38
     Quant
    0.38
     action
    0.38
    ACTION
    0.38
    行动
    0.38
    antiation
    0.37
     Extras
    0.37
     Launch
    0.37
    POSITIVE LOGITS
     pm
    0.69
     PM
    0.67
    pm
    0.64
    res
    0.56
    PM
    0.55
     पीएम
    0.54
    ContextCompat
    0.50
     res
    0.50
    DialogInterface
    0.46
     syncing
    0.46
    Act Density 0.000%

    No Known Activations