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

    Neuronpedia

    INDEX
    Explanations

    multiple choice O markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ń
    0.42
    fony
    0.41
    ne
    0.41
    NE
    0.41
    šnje
    0.40
    uly
    0.39
    rimps
    0.39
    𝘂
    0.38
    PDE
    0.38
    UMIRE
    0.37
    POSITIVE LOGITS
     tired
    0.39
     cracked
    0.38
     tiredness
    0.38
     consenting
    0.37
     Cracked
    0.37
     Raff
    0.37
     raf
    0.37
     alternate
    0.36
     adventure
    0.35
     Mous
    0.35
    Act Density 0.010%

    No Known Activations