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

    Neuronpedia

    INDEX
    Explanations

    breaking down complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वाले
    0.40
    旺
    0.38
    ୧
    0.38
    各種
    0.38
    ogr
    0.38
    ISTANCE
    0.38
     વિવિધ
    0.37
    ଝ
    0.37
    Duck
    0.37
     تقديم
    0.36
    POSITIVE LOGITS
     unquestionably
    0.45
    馚
    0.43
     thats
    0.41
     právě
    0.40
     außergewöhn
    0.39
     extrêmement
    0.38
    鑒
    0.38
     ausgest
    0.38
    աշ
    0.38
     unmittelbar
    0.38
    Act Density 0.016%

    No Known Activations