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

    Neuronpedia

    INDEX
    Explanations

    code installation commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    3.00
    ـ
    1.65
    ــ
    1.51
    -|
    1.49
    -*
    1.46
     -
    1.45
     eigen
    1.45
    -"
    1.45
    -...
    1.43
    -+
    1.42
    POSITIVE LOGITS
    এর
    2.60
    themed
    1.70
    SNAPSHOT
    1.61
    இல்
    1.60
    ஆம்
    1.56
    glazed
    1.54
    োনাম
    1.53
    tsó
    1.53
    ките
    1.53
    infodisc
    1.52
    Act Density 0.253%

    No Known Activations