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

    Neuronpedia

    INDEX
    Explanations

    guests joining show

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .acquire
    -0.07
    Meeting
    -0.07
    setDisplay
    -0.07
    ///↵↵
    -0.07
    .ReadAll
    -0.07
    .eql
    -0.07
    ᥴ
    -0.07
    /movie
    -0.07
     ספר
    -0.07
    .deep
    -0.07
    POSITIVE LOGITS
     optional
    0.06
     online
    0.06
    ℰ
    0.06
     phantom
    0.06
     butt
    0.06
    宏
    0.06
     welcomes
    0.06
    icate
    0.06
     backward
    0.06
    而在
    0.06
    Act Density 0.011%

    No Known Activations