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

    Neuronpedia

    INDEX
    Explanations

    Congress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Create
    -0.06
    _DSP
    -0.06
    .lucene
    -0.06
    .ArrayAdapter
    -0.06
    YO
    -0.06
     fö
    -0.06
     такое
    -0.06
     egy
    -0.06
    Caption
    -0.06
    ادث
    -0.05
    POSITIVE LOGITS
    inations
    0.07
     Montreal
    0.07
     suppression
    0.07
     readiness
    0.07
     patterns
    0.07
     Patterns
    0.07
    preserve
    0.06
    PX
    0.06
    ess
    0.06
    _ARROW
    0.06
    Act Density 0.000%

    No Known Activations