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

    Neuronpedia

    INDEX
    Explanations

    news and science articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     closet
    0.56
    .
    0.56
     검색
    0.55
     grounds
    0.55
    掟
    0.54
     figurative
    0.54
     putting
    0.54
    에
    0.54
    ..
    0.53
     fiyat
    0.53
    POSITIVE LOGITS
    εύ
    0.63
    েস
    0.58
    Php
    0.58
     publicación
    0.57
     Phú
    0.57
    ಜ್ಯ
    0.56
    Ն
    0.56
    ና
    0.56
    كمال
    0.55
     Macri
    0.55
    Act Density 0.020%

    No Known Activations