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

    Neuronpedia

    INDEX
    Explanations

    explaining or defining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataLoader
    0.45
     decid
    0.44
    Fond
    0.43
     orb
    0.43
     pal
    0.43
     candle
    0.43
     pendulum
    0.43
    AndTime
    0.42
    Prod
    0.42
     protector
    0.42
    POSITIVE LOGITS
    一定
    0.50
    稱為
    0.44
    oszt
    0.43
     anschauen
    0.42
     உதாரணமாக
    0.42
    細胞
    0.41
    譬
    0.41
    ни
    0.40
    ের
    0.40
    например
    0.40
    Act Density 0.001%

    No Known Activations