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

    Neuronpedia

    INDEX
    Explanations

    emphasized terms indicating significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    especially, mainly, above all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.52
     myſelf
    -0.49
     sandero
    -0.48
    windowFixed
    -0.47
     matrícula
    -0.45
     createState
    -0.45
     ſal
    -0.45
     Zitron
    -0.45
     ſta
    -0.44
     ainfi
    -0.44
    POSITIVE LOGITS
     vooral
    1.09
     allem
    1.08
     soprattutto
    1.05
     surtout
    1.03
     hlavně
    0.87
     především
    0.82
    besondere
    0.81
     sobretudo
    0.81
     principalmente
    0.80
     terutama
    0.79
    Act Density 0.007%

    No Known Activations