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

    Neuronpedia

    INDEX
    Explanations

    structural arrangement markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exemple
    -0.06
    _compat
    -0.06
     zone
    -0.06
    .Annotations
    -0.06
     ω
    -0.06
    és
    -0.06
    cs
    -0.06
    _env
    -0.06
     drums
    -0.06
     monitored
    -0.06
    POSITIVE LOGITS
     revelations
    0.07
    0.07
    azor
    0.06
    らしい
    0.06
    องจาก
    0.06
    。",↵
    0.06
    scores
    0.06
    abcdefghijkl
    0.06
    _footer
    0.06
     Král
    0.06
    Act Density 0.229%

    No Known Activations