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

    Neuronpedia

    INDEX
    Explanations

    Code and cooking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obesity
    -0.09
    Flags
    -0.09
    .Flags
    -0.08
     diverted
    -0.08
    career
    -0.08
     flags
    -0.08
    _flags
    -0.08
    flag
    -0.08
     Flags
    -0.08
     FLAG
    -0.08
    POSITIVE LOGITS
    -toggler
    0.09
     Nok
    0.08
     меж
    0.08
    -spacing
    0.08
     <!
    0.08
     alternating
    0.08
    _nested
    0.08
     expensive
    0.07
     separator
    0.07
     magnificent
    0.07
    Act Density 0.014%

    No Known Activations