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

    Neuronpedia

    INDEX
    Explanations

    state changes or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semi
    0.47
     ridge
    0.46
     comprimento
    0.46
     geomét
    0.46
     brush
    0.46
     scaler
    0.46
     expense
    0.44
     visor
    0.44
     linear
    0.44
     techniques
    0.44
    POSITIVE LOGITS
    बारक
    0.47
    Roasted
    0.46
    ayeva
    0.45
    hetam
    0.45
    uland
    0.42
     Mayweather
    0.42
     netizens
    0.42
    ikut
    0.41
    ihad
    0.41
     시민
    0.41
    Act Density 0.007%

    No Known Activations