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

    Neuronpedia

    INDEX
    Explanations

    things starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !";
    0.54
    !\
    0.51
    !".
    0.51
    !:
    0.50
    !';
    0.49
    !")
    0.47
    !!"
    0.47
    !')
    0.46
    !]
    0.46
    !",
    0.46
    POSITIVE LOGITS
     Tuesday
    0.50
     October
    0.48
     hadn
    0.48
     Tuesdays
    0.47
     November
    0.47
     pourtant
    0.47
     Hospice
    0.46
     spraw
    0.46
     অবশ্য
    0.46
     mornings
    0.45
    Act Density 0.059%

    No Known Activations