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

    Neuronpedia

    INDEX
    Explanations

    llama, align, VB, miner, data, ASP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PAssignment
    0.41
     Qxe
    0.36
    𝖙
    0.36
     Enemies
    0.36
    0.36
    ଵ
    0.35
     டிகிரி
    0.35
     tempHeader
    0.35
     @_
    0.34
    Ｑ
    0.33
    POSITIVE LOGITS
    ․
    0.66
     डॉट
    0.58
    .,"
    0.53
    .$.
    0.53
    ./
    0.52
    .​
    0.51
    ܂
    0.50
    .*
    0.50
     dot
    0.50
    .,
    0.49
    Act Density 0.059%

    No Known Activations