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

    Neuronpedia

    INDEX
    Explanations

    code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.54
     anhyd
    -0.50
     assemblies
    -0.48
     sight
    -0.47
     lenker
    -0.46
     preſent
    -0.46
     neceff
    -0.45
    ”!
    -0.44
     Louvain
    -0.44
    براير
    -0.44
    POSITIVE LOGITS
    aroos
    0.60
    كذا
    0.56
     שוליים
    0.55
     nakalista
    0.54
    hatikan
    0.54
    covery
    0.53
    Архівовано
    0.52
     réputation
    0.52
     onOptions
    0.52
    phosa
    0.52
    Act Density 0.007%

    No Known Activations