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

    Neuronpedia

    INDEX
    Explanations

    action or answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orough
    0.86
     berikut
    0.86
    idaknya
    0.85
    estimate
    0.84
    ❤️❤️
    0.83
    ‼️
    0.82
    ❣️
    0.82
    olisian
    0.82
    ance
    0.81
    ätzen
    0.81
    POSITIVE LOGITS
     Hint
    0.86
                                   
    0.81
    前的
    0.80
     Express
    0.79
     Auditorium
    0.75
    hint
    0.73
    ________________
    0.72
     vecchio
    0.72
     Historical
    0.71
    Hint
    0.71
    Act Density 0.069%

    No Known Activations