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

    Neuronpedia

    INDEX
    Explanations

    ever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iversit
    -0.07
    нання
    -0.07
     erle
    -0.06
    played
    -0.06
     рай
    -0.06
     Folk
    -0.06
     Lent
    -0.06
     sabot
    -0.06
     terme
    -0.06
    _producto
    -0.06
    POSITIVE LOGITS
     Whoever
    0.09
     whoever
    0.08
     wherever
    0.08
     whichever
    0.07
    ichever
    0.07
    sl
    0.07
    joining
    0.06
    Histor
    0.06
    vez
    0.06
    的小
    0.06
    Act Density 0.003%

    No Known Activations