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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gings
    -0.08
    _orig
    -0.07
     fists
    -0.06
    **↵↵
    -0.06
    prit
    -0.06
    що
    -0.06
    Owner
    -0.06
     {↵↵
    -0.06
    Selective
    -0.06
     refrigerator
    -0.06
    POSITIVE LOGITS
     FIFO
    0.07
     schizophren
    0.06
     veterinary
    0.06
     Weinstein
    0.06
     condol
    0.06
     мы
    0.06
     Normal
    0.06
    .Err
    0.06
     reviewer
    0.06
     widening
    0.06
    Act Density 0.025%

    No Known Activations