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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Actually
    -0.08
     sixteen
    -0.07
    Insurance
    -0.07
     Song
    -0.07
     modifications
    -0.07
     coins
    -0.07
    man
    -0.07
    Function
    -0.07
     banged
    -0.07
    そうな
    -0.07
    POSITIVE LOGITS
     >
    0.10
    еты
    0.08
    EW
    0.08
    潜
    0.08
    ewe
    0.08
    EP
    0.08
    ET
    0.07
     >>
    0.07
     EU
    0.07
     预
    0.07
    Act Density 0.047%

    No Known Activations