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

    Neuronpedia

    INDEX
    Explanations

    ake/rake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interfaces
    -0.07
     generals
    -0.06
     deprivation
    -0.06
    /'↵
    -0.06
     fluorescence
    -0.06
     trophies
    -0.06
    Forward
    -0.06
    たちは
    -0.06
    ("");↵↵
    -0.06
     dye
    -0.06
    POSITIVE LOGITS
     Rak
    0.13
     Tolkien
    0.13
     Milton
    0.12
     rake
    0.11
     Otto
    0.11
    olkien
    0.11
     rak
    0.10
     Sudan
    0.08
     Byron
    0.08
     Carlton
    0.07
    Act Density 0.004%

    No Known Activations