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

    Neuronpedia

    INDEX
    Explanations

    detailed plans and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.48
    лды
    0.43
     Conductivity
    0.42
    ल्ल
    0.42
    ermark
    0.40
     interferometer
    0.40
     Crude
    0.40
     brom
    0.39
     уско
    0.39
     asymptotic
    0.39
    POSITIVE LOGITS
    म्ह
    0.47
     gön
    0.47
    null
    0.46
     Dritt
    0.45
    και
    0.44
    +]
    0.43
    来自
    0.42
     inclu
    0.42
    __,
    0.42
    inherit
    0.42
    Act Density 0.000%

    No Known Activations