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

    Neuronpedia

    INDEX
    Explanations

    fight the new drug

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मालूम
    0.38
     područ
    0.38
    可靠
    0.37
     membrana
    0.36
     Κο
    0.36
    یات
    0.36
     மேலே
    0.35
    桡
    0.35
    <unused79>
    0.35
     previewBuilder
    0.35
    POSITIVE LOGITS
     utilisez
    0.45
    yourself
    0.42
    version
    0.42
    installation
    0.42
     (
    0.40
     yourself
    0.40
    fake
    0.40
    chosen
    0.39
     Yourself
    0.38
    ၂
    0.38
    Act Density 0.007%

    No Known Activations