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

    Neuronpedia

    INDEX
    Explanations

    academic cita

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Isometric
    0.58
     সর্বনিম্ন
    0.57
     Operand
    0.56
     silos
    0.56
     INDUSTRIAL
    0.55
    ())->
    0.55
     PHD
    0.55
     Silicone
    0.55
     mutual
    0.55
     தொழில்
    0.55
    POSITIVE LOGITS
     cited
    0.62
     cita
    0.58
     cite
    0.57
    refs
    0.56
     cites
    0.52
    cyan
    0.52
    ]{
    0.52
     Cited
    0.51
    cite
    0.51
    틴
    0.50
    Act Density 0.000%

    No Known Activations