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

    Neuronpedia

    INDEX
    Explanations

    links and determinism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    0.56
    oglio
    0.52
    ੋਰ
    0.50
    க்கி
    0.50
    تر
    0.47
    ari
    0.46
    ars
    0.46
    iter
    0.46
    ugio
    0.45
    is
    0.44
    POSITIVE LOGITS
     réduite
    0.51
     அதை
    0.48
     Brought
    0.47
    utory
    0.47
     அவற்றை
    0.47
     у
    0.47
     ג
    0.46
     በኋላ
    0.46
     Timurtaş
    0.45
     tableaux
    0.45
    Act Density 0.001%

    No Known Activations