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

    Neuronpedia

    INDEX
    Explanations

    data manipulation functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ponents
    0.39
    resolved
    0.39
    deux
    0.38
    opération
    0.38
     કરો
    0.38
    lée
    0.38
    anal
    0.36
     résolution
    0.36
    انے
    0.36
     resolv
    0.36
    POSITIVE LOGITS
     सिप
    0.38
     Perf
    0.37
    WALLET
    0.36
     dif
    0.35
     wallets
    0.35
     ब्रह्
    0.35
     akh
    0.34
    واری
    0.34
     Wallet
    0.34
     Price
    0.33
    Act Density 0.001%

    No Known Activations