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

    Neuronpedia

    INDEX
    Explanations

    things like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.26
     ​​
    1.24
    <0x80>
    1.15
    та
    1.10
    t
    1.00
    αι
    0.94
    <0x98>
    0.93
    BAR
    0.92
    т
    0.92
    на
    0.91
    POSITIVE LOGITS
    it
    1.30
     fatores
    1.10
     maximizes
    1.09
     públicos
    1.07
     ثانيه
    1.06
     fontos
    1.05
     relatifs
    1.05
     notably
    1.04
     безопасности
    1.04
    xas
    1.04
    Act Density 0.092%

    No Known Activations