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

    Neuronpedia

    INDEX
    Explanations

    `<!DOCTYPE html>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pembroke
    0.36
     பரு
    0.36
     marcada
    0.36
    ENG
    0.36
    टन
    0.35
     muestran
    0.35
     marcado
    0.35
     शरद
    0.34
    鱈
    0.34
     fibrillation
    0.34
    POSITIVE LOGITS
    DOCTYPE
    0.80
    doctype
    0.62
    CDATA
    0.57
     doct
    0.57
    --
    0.56
     `--
    0.56
    ---->
    0.53
     --
    0.51
    <!
    0.50
     //-->
    0.48
    Act Density 0.005%

    No Known Activations