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

    Neuronpedia

    INDEX
    Explanations

    event reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hull
    0.67
     ئى
    0.67
    ীয়
    0.61
    Hull
    0.61
     ngờ
    0.60
     offer
    0.60
    ದಲ್ಲಿ
    0.59
     rosy
    0.58
     Lévy
    0.57
     conduct
    0.57
    POSITIVE LOGITS
     besonderen
    0.85
     comptes
    0.83
     তাহাদিগকে
    0.82
    સા
    0.81
    感谢
    0.80
     তাহাদিগের
    0.80
    Gracias
    0.80
     главным
    0.80
    Wedding
    0.79
    Tile
    0.79
    Act Density 0.000%

    No Known Activations