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

    Neuronpedia

    INDEX
    Explanations

    API keys and tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     STD
    0.32
     Agile
    0.32
     Imagination
    0.32
    ens
    0.31
    𝑛
    0.31
     Entrepreneur
    0.31
     Heels
    0.31
     ECD
    0.31
     Volvo
    0.31
    igueur
    0.31
    POSITIVE LOGITS
     gamanam
    0.33
    Π
    0.32
     ڪري
    0.31
    κ
    0.31
    Smoke
    0.30
     previstas
    0.30
    াহিয়া
    0.30
    Prof
    0.30
     posY
    0.30
    Grande
    0.29
    Act Density 0.009%

    No Known Activations