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

    Neuronpedia

    INDEX
    Explanations

    days, duration, or count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    osion
    1.08
     disso
    0.98
    PERTY
    0.96
    PHONY
    0.95
    к
    0.95
    ｋ
    0.94
     decoded
    0.94
     mismos
    0.93
     daqui
    0.92
    м
    0.91
    POSITIVE LOGITS
    ことになる
    1.24
    ש
    0.99
    is
    0.96
     süre
    0.94
    night
    0.94
    lived
    0.91
    น
    0.90
     giorni
    0.87
    ților
    0.87
    ことにより
    0.86
    Act Density 0.073%

    No Known Activations