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

    Neuronpedia

    INDEX
    Explanations

    Code/UI elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     потол
    -0.07
     Laws
    -0.06
    CORE
    -0.06
    Segments
    -0.06
     Poetry
    -0.06
     Everything
    -0.06
     MBA
    -0.06
     Haupt
    -0.06
    _sibling
    -0.06
     distressed
    -0.06
    POSITIVE LOGITS
     دی
    0.06
     baptism
    0.06
    ِي
    0.06
     bilin
    0.06
    keterangan
    0.06
     лей
    0.06
     guideline
    0.06
    /do
    0.06
     paren
    0.06
     پژ
    0.06
    Act Density 0.067%

    No Known Activations