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

    Neuronpedia

    INDEX
    Explanations

    decades of technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    after
    0.46
    NING
    0.46
    membered
    0.45
    চনার
    0.45
     Afterward
    0.45
    Fs
    0.44
     Bagg
    0.43
     after
    0.43
    From
    0.43
     Doesn
    0.42
    POSITIVE LOGITS
     maintenir
    0.52
     proprement
    0.52
    虛
    0.48
     maladie
    0.47
    價格
    0.47
     vise
    0.46
     transfert
    0.46
     humide
    0.46
    gendes
    0.46
     wyra
    0.46
    Act Density 0.001%

    No Known Activations