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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kü
    0.68
    StrictMode
    0.65
    CUSS
    0.64
     Kyoto
    0.63
     Hyatt
    0.63
     Cuomo
    0.63
     Blackpool
    0.61
     Hedgehog
    0.60
     Café
    0.60
    取扱
    0.60
    POSITIVE LOGITS
     impairs
    0.60
    istin
    0.60
     authored
    0.58
     phenols
    0.58
     characterized
    0.57
     szól
    0.57
     effected
    0.57
     whos
    0.57
     fieldValue
    0.56
     hampers
    0.56
    Act Density 0.000%

    No Known Activations