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

    Neuronpedia

    INDEX
    Explanations

    null, none, empty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಾನೂ
    0.37
     เด้อ
    0.37
     HEAT
    0.36
    »:
    0.35
     COMB
    0.35
     devez
    0.34
     EDITION
    0.34
    मार्ग
    0.34
     CONSULT
    0.34
     पदार्थों
    0.33
    POSITIVE LOGITS
     ,
    0.35
    除非
    0.33
     空
    0.32
    为空
    0.32
    0.31
    avor
    0.31
     empty
    0.31
    <tr>
    0.30
    atever
    0.30
     unnamed
    0.29
    Act Density 0.173%

    No Known Activations