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

    Neuronpedia

    INDEX
    Explanations

    environment variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Breaking
    -0.07
     containers
    -0.07
    .lookup
    -0.06
     furnace
    -0.06
     PCs
    -0.06
     Nach
    -0.06
    Seek
    -0.06
     Member
    -0.06
    CAST
    -0.06
    urr
    -0.06
    POSITIVE LOGITS
     yıldır
    0.07
     chancellor
    0.07
     pla
    0.06
     Dortmund
    0.06
    .lex
    0.06
    ())
↵
    0.06
    icensing
    0.06
    =""↵
    0.06
    xiv
    0.06
    ínu
    0.06
    Act Density 0.006%

    No Known Activations