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

    Neuronpedia

    INDEX
    Explanations

    adding content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    汾
    0.39
     письма
    0.38
     Mest
    0.37
    krb
    0.37
     computeEncoder
    0.37
    김포
    0.37
     கூட்ட
    0.36
     Natalie
    0.36
    seo
    0.35
     kelt
    0.35
    POSITIVE LOGITS
    мент
    0.42
     cameras
    0.41
    वीं
    0.41
    нду
    0.38
     subunit
    0.37
    Cameras
    0.36
    ืน
    0.36
    XM
    0.36
    렉
    0.35
    摄像
    0.35
    Act Density 0.000%

    No Known Activations