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

    Neuronpedia

    INDEX
    Explanations

    common word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.21
    ،
    0.19
    :
    0.19
    ↵
    0.18
     inet
    0.18
    、
    0.18
     are
    0.18
    ,
    0.18
    2
    0.18
     erase
    0.17
    POSITIVE LOGITS
    apping
    0.23
    abbing
    0.21
    addling
    0.20
    uggling
    0.20
    uffling
    0.20
    âteaux
    0.20
    idding
    0.20
    <unused646>
    0.19
     कॉल्ड
    0.18
    ॉक
    0.18
    Act Density 0.266%

    No Known Activations