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

    Neuronpedia

    INDEX
    Explanations

    that/which followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asmuch
    1.46
    elni
    1.44
    avacanam
    1.43
    reng
    1.40
    <0x80>
    1.34
    ෂ
    1.34
     eğer
    1.34
     divina
    1.31
     dolayı
    1.29
    ও
    1.29
    POSITIVE LOGITS
    й
    2.03
    1.56
    д
    1.53
     knows
    1.41
    ት
    1.34
    <bos>
    1.34
     يعرف
    1.34
    b
    1.31
    лакти
    1.30
    ഥ
    1.30
    Act Density 0.296%

    No Known Activations