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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kd
    -0.07
     ALS
    -0.07
    Writing
    -0.06
    -opening
    -0.06
     Oracle
    -0.06
     Successfully
    -0.06
     Reno
    -0.06
    .getChannel
    -0.06
    605
    -0.06
     locations
    -0.06
    POSITIVE LOGITS
    olik
    0.06
    _INFORMATION
    0.06
     treffen
    0.06
     jumped
    0.06
     ",
    0.06
     Relevant
    0.06
    (rows
    0.06
    ologi
    0.06
    \Base
    0.05
    QUERY
    0.05
    Act Density 0.196%

    No Known Activations