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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     údaj
    -0.07
     Род
    -0.07
     FILES
    -0.07
     defaults
    -0.07
     NF
    -0.07
    /problem
    -0.06
    (local
    -0.06
     sân
    -0.06
     HOUSE
    -0.06
    猛
    -0.06
    POSITIVE LOGITS
     antid
    0.06
    A
    0.06
    �
    0.06
     μα
    0.06
    escort
    0.06
    abol
    0.06
    なく
    0.06
    Limit
    0.06
    \
    0.06
    brid
    0.06
    Act Density 0.000%

    No Known Activations