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

    Neuronpedia

    INDEX
    Explanations

    references to award-winning films and their categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colare
    -0.37
    amerikanischer
    -0.37
     Var
    -0.35
     terecht
    -0.34
     Genova
    -0.33
    futter
    -0.33
     Maurer
    -0.32
     Punkt
    -0.32
    atics
    -0.32
     Pun
    -0.32
    POSITIVE LOGITS
    best
    0.82
    Best
    0.81
    BEST
    0.80
     best
    0.78
     BEST
    0.76
     Best
    0.73
     beſt
    0.66
     terbaik
    0.63
     nakalista
    0.62
     дописавши
    0.61
    Act Density 0.014%

    No Known Activations