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

    Neuronpedia

    INDEX
    Explanations

    : and -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unreal
    -0.07
    ultural
    -0.07
    .sat
    -0.06
    ayan
    -0.06
    ilin
    -0.06
     swaps
    -0.06
     있는
    -0.06
     redundancy
    -0.06
     detergent
    -0.06
    avit
    -0.06
    POSITIVE LOGITS
    ame
    0.07
    Ignore
    0.07
    _Function
    0.06
     eigentlich
    0.06
    ClassName
    0.06
    ER
    0.06
    each
    0.06
    /jpeg
    0.06
    .latest
    0.06
    ...'
    0.06
    Act Density 0.011%

    No Known Activations