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

    Neuronpedia

    INDEX
    Explanations

    increasingly unhinged or unnerved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    डी
    0.39
    Supply
    0.36
     উত্স
    0.36
    uz
    0.36
     Supply
    0.36
    ழக
    0.36
     Levant
    0.36
    Loy
    0.36
     yer
    0.35
    সু
    0.35
    POSITIVE LOGITS
     pess
    0.42
     تربيع
    0.40
    ופן
    0.40
    itelisted
    0.39
     antigenic
    0.39
    ータル
    0.39
     optimal
    0.38
    injlim
    0.38
     inap
    0.38
    နယ်
    0.38
    Act Density 0.001%

    No Known Activations