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

    Neuronpedia

    INDEX
    Explanations

    spread globally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oles
    0.89
    ola
    0.89
    ned
    0.82
    led
    0.78
    spent
    0.77
    ip
    0.77
    oleon
    0.77
    rien
    0.77
    om
    0.75
    ren
    0.75
    POSITIVE LOGITS
    ות
    1.02
    ر
    1.02
    ために
    0.99
     dissemination
    0.98
     Spread
    0.96
     spread
    0.96
     transmis
    0.91
     especies
    0.91
     diffusione
    0.91
     फैलाने
    0.89
    Act Density 0.036%

    No Known Activations