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

    Neuronpedia

    INDEX
    Explanations

    interpersonal relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MART
    -0.07
    .ext
    -0.07
    _INITIAL
    -0.07
    _bias
    -0.06
    _FORWARD
    -0.06
    agedList
    -0.06
     ép
    -0.06
    enumerate
    -0.06
    AndServe
    -0.06
    marginTop
    -0.06
    POSITIVE LOGITS
     skeletons
    0.07
     slun
    0.06
     KC
    0.06
     todos
    0.06
     फर
    0.06
     Entity
    0.06
     privat
    0.06
     хозяй
    0.06
     omas
    0.06
    (TR
    0.05
    Act Density 0.024%

    No Known Activations