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

    Neuronpedia

    INDEX
    Explanations

    you or user actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enter
    0.66
     Enter
    0.65
     enter
    0.63
     Select
    0.61
     hãy
    0.55
     select
    0.54
     ENTER
    0.54
     Choose
    0.54
     请
    0.54
    select
    0.53
    POSITIVE LOGITS
    received
    0.46
     received
    0.44
    selected
    0.40
     Received
    0.40
     selected
    0.40
     Selected
    0.40
    SELECTED
    0.40
    чені
    0.39
    Received
    0.39
    emun
    0.39
    Act Density 0.003%

    No Known Activations