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

    Neuronpedia

    INDEX
    Explanations

    technical terms and foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.36
     Осо
    1.17
    ếu
    1.12
    iglich
    1.11
    islam
    1.09
     بخش
    1.08
    ι
    1.06
     이르
    1.06
    д
    1.05
    حة
    1.05
    POSITIVE LOGITS
     assh
    1.34
     endpoints
    1.33
    ជំងឺ
    1.33
    }')
    1.33
     Hadamard
    1.33
     bullshit
    1.33
    listOf
    1.32
    䣵
    1.30
     entrees
    1.30
    领域的
    1.29
    Act Density 0.000%

    No Known Activations