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

    Neuronpedia

    INDEX
    Explanations

    your + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.28
    没有
    0.28
    ହା
    0.28
    ه
    0.28
     our
    0.27
     for
    0.27
    a
    0.26
    我们
    0.26
     formidable
    0.26
    シ
    0.26
    POSITIVE LOGITS
     तुमचे
    0.25
     yourself
    0.25
     jezelf
    0.25
     तुमच्या
    0.24
     акча
    0.24
     saate
    0.24
     sendiri
    0.24
    oliberal
    0.24
     اگه
    0.24
     own
    0.24
    Act Density 0.533%

    No Known Activations