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

    Neuronpedia

    INDEX
    Explanations

    why... explains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pabbaj
    0.49
     dokter
    0.49
    ពី
    0.46
     primeiras
    0.44
     dimas
    0.44
     antiga
    0.44
     plantas
    0.44
     bilg
    0.44
     trataro
    0.44
     piccola
    0.44
    POSITIVE LOGITS
     Fortnite
    0.49
     Playoffs
    0.49
     Algorithm
    0.47
    Fourth
    0.46
     Championship
    0.45
     Spotlight
    0.44
     FOM
    0.44
     ultimately
    0.43
    Algorithm
    0.42
     Prep
    0.42
    Act Density 0.020%

    No Known Activations