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

    Neuronpedia

    INDEX
    Explanations

    surgical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ac
    -0.06
    쇼
    -0.06
    层
    -0.06
    ț
    -0.06
     cues
    -0.06
    Putting
    -0.06
    工程
    -0.06
    Matthew
    -0.06
    HexString
    -0.06
    ν
    -0.06
    POSITIVE LOGITS
    -final
    0.07
     surtout
    0.07
    visor
    0.06
    anı
    0.06
    _qos
    0.06
    Successfully
    0.06
     ((!
    0.06
     réalis
    0.06
     MIME
    0.06
     ".",
    0.06
    Act Density 0.012%

    No Known Activations