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

    Neuronpedia

    INDEX
    Explanations

    provider for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ponemos
    0.82
    Meyer
    0.76
     cfg
    0.75
    mi
    0.73
    Trend
    0.73
     острова
    0.72
    ঙ্গ
    0.71
    accident
    0.70
     certified
    0.70
    dcs
    0.69
    POSITIVE LOGITS
     improvised
    0.69
     /ˈ
    0.68
    (^
    0.67
     fadeInUp
    0.67
     setTimeout
    0.66
     amoureux
    0.66
     ഇന്ത്യന്‍
    0.63
     Schweizer
    0.63
    akkhan
    0.63
    chnik
    0.63
    Act Density 0.004%

    No Known Activations