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

    Neuronpedia

    INDEX
    Explanations

    dynamic programming states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    particularly
    0.76
    especially
    0.74
     szczególnie
    0.73
     particularly
    0.69
     özellikle
    0.67
    belum
    0.66
     especially
    0.66
    ელია
    0.65
     особенно
    0.65
    menuid
    0.65
    POSITIVE LOGITS
     ▸
    0.70
     hine
    0.64
     coalescence
    0.64
    ᒃ
    0.64
     inverter
    0.62
     silico
    0.62
     cleverly
    0.61
     copol
    0.61
     coarsely
    0.61
                                 
    0.60
    Act Density 0.002%

    No Known Activations