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

    Neuronpedia

    INDEX
    Explanations

    describing plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     معامل
    0.48
     medic
    0.48
    medic
    0.47
    uptime
    0.46
     राक्ष
    0.45
     रोकथाम
    0.44
    isant
    0.44
     cunning
    0.44
     inept
    0.44
     materialistic
    0.44
    POSITIVE LOGITS
     espaços
    0.51
     Navy
    0.47
     furono
    0.47
     élabor
    0.44
    ції
    0.44
     führt
    0.44
     était
    0.43
    াড়
    0.43
    ož
    0.43
     mendorong
    0.43
    Act Density 0.000%

    No Known Activations