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

    Neuronpedia

    INDEX
    Explanations

    Timestamps/Measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trek
    -0.07
     visto
    -0.07
    -medium
    -0.07
    =this
    -0.07
     Presidential
    -0.06
    otes
    -0.06
     zpráv
    -0.06
     offsetX
    -0.06
    hic
    -0.06
    عة
    -0.06
    POSITIVE LOGITS
    地址
    0.08
     moh
    0.06
     SSL
    0.06
    »↵↵
    0.06
    .AllArgsConstructor
    0.06
    .FileReader
    0.06
    (CONFIG
    0.06
    >D
    0.06
    meg
    0.06
    .emplace
    0.06
    Act Density 0.001%

    No Known Activations