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

    Neuronpedia

    INDEX
    Explanations

    Text Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CTL
    -0.07
     Pe
    -0.06
     SSP
    -0.06
    Signal
    -0.06
     def
    -0.06
    ^\
    -0.06
    .staff
    -0.06
     X
    -0.06
     elkaar
    -0.06
    -m
    -0.06
    POSITIVE LOGITS
     bana
    0.07
     mens
    0.07
    ."]↵
    0.07
    uctor
    0.06
    σμο
    0.06
     erw
    0.06
     Cumhurbaşkanı
    0.06
    tra
    0.06
    pok
    0.06
    ечно
    0.06
    Act Density 0.012%

    No Known Activations