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

    Neuronpedia

    INDEX
    Explanations

    definitely the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उक्त
    0.34
     одежда
    0.29
    सेप्शन
    0.29
     наличи
    0.29
     впечат
    0.29
     велосипе
    0.29
    луйста
    0.28
     coleção
    0.28
     uveden
    0.28
    岧
    0.28
    POSITIVE LOGITS
    c
    0.28
    p
    0.28
    le
    0.27
    E
    0.27
    H
    0.27
    S
    0.27
    r
    0.26
    ol
    0.26
     K
    0.26
     F
    0.25
    Act Density 0.029%

    No Known Activations