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

    Neuronpedia

    INDEX
    Explanations

    My Programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bạn
    0.34
     \(
    0.32
    <unused2164>
    0.32
    ('./
    0.31
    流
    0.31
    merged
    0.30
    fungen
    0.30
    <unused2169>
    0.30
    matmul
    0.29
     eluted
    0.29
    POSITIVE LOGITS
     outros
    0.40
     otras
    0.39
    以外の
    0.38
     intento
    0.38
     حاول
    0.38
    的其他
    0.38
     quirks
    0.37
     sendiri
    0.36
     peran
    0.36
     langue
    0.36
    Act Density 0.545%

    No Known Activations