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

    Neuronpedia

    INDEX
    Explanations

    address placeholder in contact lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ນີ້
    0.31
     nouns
    0.29
    ມັນ
    0.29
     fenómenos
    0.29
     videomuz
    0.29
     ứng
    0.28
     vidrio
    0.28
     surnames
    0.28
    មនុស្ស
    0.28
     দুর্ঘটনা
    0.27
    POSITIVE LOGITS
    ↵↵
    0.38
    /
    0.31
    er
    0.31
    ）
    0.31
    affiliated
    0.30
    validate
    0.30
    િમ
    0.29
    confirmed
    0.29
    𝐫
    0.29
    ers
    0.29
    Act Density 0.030%

    No Known Activations