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

    Neuronpedia

    INDEX
    Explanations

    youtube thumbnails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cochrane
    0.44
     Schatz
    0.43
     Dato
    0.43
     للص
    0.43
    ச்சு
    0.43
    竴
    0.43
     Foire
    0.42
     Гон
    0.42
    ᄍ
    0.41
     दत्ता
    0.41
    POSITIVE LOGITS
    lo
    0.47
    お店
    0.44
    !!!!!
    0.44
     exchanges
    0.43
     hems
    0.43
     hogares
    0.43
    d
    0.43
     containers
    0.42
     aisles
    0.42
     cafes
    0.41
    Act Density 0.001%

    No Known Activations