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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Soul
    -0.08
    .FileName
    -0.07
    Pa
    -0.07
    NAME
    -0.07
     Grave
    -0.07
    魂
    -0.06
    Corner
    -0.06
    Deck
    -0.06
     Samp
    -0.06
    Bound
    -0.06
    POSITIVE LOGITS
    Markers
    0.07
    ：↵↵
    0.07
     toppings
    0.07
    시
    0.06
     acceptance
    0.06
    CLEAR
    0.06
     continuation
    0.06
     дост
    0.06
    ;↵↵
    0.06
     practices
    0.06
    Act Density 0.021%

    No Known Activations