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

    Neuronpedia

    INDEX
    Explanations

    Marion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marion
    -0.81
    Marion
    -0.62
     K
    -0.53
     cam
    -0.47
     Liu
    -0.47
     So
    -0.46
     F
    -0.45
    semitism
    -0.45
    nette
    -0.45
     Cam
    -0.44
    POSITIVE LOGITS
    uxxxx
    1.00
    LookAnd
    0.93
     EnglishChoose
    0.90
    IsContent
    0.87
     ―――――
    0.87
    expandindo
    0.84
     jadx
    0.84
     ་་
    0.84
     myſelf
    0.81
    ########.
    0.80
    Act Density 0.049%

    No Known Activations