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

    Neuronpedia

    INDEX
    Explanations

    language learning and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.32
     viêm
    0.26
     እና
    0.25
     recordó
    0.25
     น้ำ
    0.25
    आई
    0.25
     và
    0.25
     joyería
    0.24
     problemática
    0.24
     rượu
    0.24
    POSITIVE LOGITS
    ות
    0.44
    ون
    0.37
    ’
    0.34
    ва
    0.33
    ل
    0.31
     pronouns
    0.30
    ר
    0.30
    ת
    0.30
    il
    0.29
    ната
    0.29
    Act Density 0.222%

    No Known Activations