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

    Neuronpedia

    INDEX
    Explanations

    creative writing prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.81
     with
    1.74
    '
    1.71
     (£
    1.44
     lược
    1.41
     reckons
    1.41
     was
    1.40
     envis
    1.39
    auan
    1.34
     is
    1.32
    POSITIVE LOGITS
     newfound
    2.91
     undefined
    2.70
    ambient
    2.69
    нных
    2.67
     fizik
    2.62
     distinct
    2.62
    tableFuture
    2.62
     respeto
    2.61
     ثاني
    2.60
     degrés
    2.59
    Act Density 0.600%

    No Known Activations