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

    Neuronpedia

    INDEX
    Explanations

    transfer load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jimmy
    0.43
    ymo
    0.41
    ଟି
    0.40
    nim
    0.40
    UV
    0.39
    maß
    0.39
     Babies
    0.39
    一个小
    0.39
    emente
    0.38
    roph
    0.38
    POSITIVE LOGITS
     unveiling
    0.42
    肨
    0.40
    கிறது
    0.38
     curling
    0.37
     Puck
    0.37
     prosp
    0.37
     mount
    0.36
     mounting
    0.36
     victoria
    0.36
     rejuven
    0.35
    Act Density 0.001%

    No Known Activations