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

    Neuronpedia

    INDEX
    Explanations

    kn words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relais
    0.93
     envi
    0.93
     recapture
    0.89
     막
    0.86
     nata
    0.84
     Hulu
    0.83
     시대
    0.82
    ท้าย
    0.82
     longitude
    0.82
    Spoiler
    0.81
    POSITIVE LOGITS
    itted
    1.14
    apsack
    1.06
    ترل
    0.97
    itting
    0.92
    ieval
    0.89
    ights
    0.89
     प्रभारी
    0.83
    ossos
    0.83
    ifed
    0.81
    ricks
    0.80
    Act Density 0.035%

    No Known Activations