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

    Neuronpedia

    INDEX
    Explanations

    code blocks and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    うれ
    -0.97
    orrhea
    -0.85
    empresas
    -0.81
    Specifik
    -0.80
     aliviar
    -0.76
     anunciar
    -0.73
     asegurado
    -0.72
    casal
    -0.69
    imedes
    -0.69
    ohistochemical
    -0.69
    POSITIVE LOGITS
     Prerequisite
    0.84
     AUF
    0.78
    Bryce
    0.78
     Dua
    0.77
     Herv
    0.77
     Soler
    0.75
     Filipina
    0.75
     Vire
    0.75
    ATER
    0.75
    setCancelable
    0.75
    Act Density 0.019%

    No Known Activations