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

    Neuronpedia

    INDEX
    Explanations

    Code-related terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，说
    -0.07
    _blend
    -0.06
    parity
    -0.06
    Unmount
    -0.06
    šky
    -0.06
     pudding
    -0.06
     答
    -0.06
    challenge
    -0.06
    ernet
    -0.06
    Pictures
    -0.06
    POSITIVE LOGITS
    141
    0.07
     stuff
    0.07
    leftright
    0.06
     wanted
    0.06
    .nextElement
    0.06
    kl
    0.06
     ascertain
    0.06
     Ні
    0.06
    ple
    0.06
    235
    0.06
    Act Density 0.066%

    No Known Activations