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

    Neuronpedia

    INDEX
    Explanations

    function returns or selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పట్ట
    0.45
     योग्य
    0.45
    怎麼樣
    0.45
    ле
    0.44
    ladesh
    0.43
    ierung
    0.42
     فيها
    0.42
    れて
    0.42
    alet
    0.41
     في
    0.41
    POSITIVE LOGITS
    Ons
    0.52
    OW
    0.50
    ή
    0.48
    Ό
    0.48
    ക്
    0.48
    Ꮡ
    0.46
    Τ
    0.46
    Χ
    0.46
    এ
    0.45
    Λ
    0.45
    Act Density 0.001%

    No Known Activations