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

    Neuronpedia

    INDEX
    Explanations

    direction and movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বসিয়
    0.75
    ここで
    0.69
    अच्छ
    0.67
     samu
    0.67
    ખ્ય
    0.67
    క్కడ
    0.65
     ძალი
    0.64
    Bottom
    0.63
     డ
    0.63
     సంగ
    0.63
    POSITIVE LOGITS
     towards
    5.12
     toward
    4.92
     Towards
    4.42
    towards
    4.31
     Toward
    4.25
    Towards
    4.20
    Toward
    3.93
     hacia
    3.92
    tow
    3.04
     verso
    2.81
    Act Density 0.583%

    No Known Activations