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

    Neuronpedia

    INDEX
    Explanations

    chart notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    íncipe
    0.40
    टेगरी
    0.39
     Brig
    0.38
    堹
    0.37
    gel
    0.36
    owało
    0.36
    пів
    0.36
    ipelago
    0.35
     उल्टा
    0.35
    หม
    0.35
    POSITIVE LOGITS
     láser
    0.52
     빠른
    0.48
    コー
    0.46
     Avoiding
    0.46
     neodymium
    0.42
     evitando
    0.41
     زینت
    0.40
     Graduates
    0.40
     caoutchouc
    0.40
     lasers
    0.40
    Act Density 0.000%

    No Known Activations