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

    Neuronpedia

    INDEX
    Explanations

    areas to explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এছাড়া
    0.45
     dependents
    0.44
     voordat
    0.44
     minerals
    0.43
     derniers
    0.42
     ferrugineux
    0.42
     pollutants
    0.41
     einfache
    0.41
     damaged
    0.40
     pollutant
    0.40
    POSITIVE LOGITS
     Patreon
    0.64
     Atlético
    0.54
     chibi
    0.52
     Alexandre
    0.51
     illustrious
    0.51
     Gareth
    0.51
     Activision
    0.49
     BAFTA
    0.48
     Ubisoft
    0.48
     auteurs
    0.48
    Act Density 0.001%

    No Known Activations