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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cardio
    -0.07
    拥有
    -0.06
    找到
    -0.06
    ellido
    -0.06
     continue
    -0.06
     Spi
    -0.06
    corn
    -0.06
     type
    -0.06
     cif
    -0.06
     ic
    -0.06
    POSITIVE LOGITS
    MainFrame
    0.07
     moderators
    0.07
    NOTE
    0.06
    .child
    0.06
    _logic
    0.06
    .Select
    0.06
     primaryKey
    0.06
     Perl
    0.06
    -million
    0.06
    .FILL
    0.06
    Act Density 0.360%

    No Known Activations