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

    Neuronpedia

    INDEX
    Explanations

    Downlink MAC, currency, Oasis, Data Explorer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हायर
    0.75
    itive
    0.70
    orent
    0.67
    andex
    0.65
    tert
    0.64
     tand
    0.64
    utin
    0.63
    terraform
    0.63
    opolitan
    0.63
    eter
    0.63
    POSITIVE LOGITS
     괜
    0.82
    ্থ
    0.80
     Chaos
    0.75
    hé
    0.74
    掃
    0.73
     連
    0.73
    Chaos
    0.72
     погру
    0.72
     मध
    0.71
     brinc
    0.70
    Act Density 0.000%

    No Known Activations