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

    Neuronpedia

    INDEX
    Explanations

    Arabic/Islamic names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agile
    0.64
     teleport
    0.64
     Terraform
    0.60
     windfall
    0.59
     dimer
    0.59
     discern
    0.59
     Byte
    0.58
     elev
    0.58
     Terrain
    0.57
     vastly
    0.57
    POSITIVE LOGITS
    arat
    0.97
    ri
    0.93
    rawy
    0.92
    awati
    0.92
    az
    0.91
    lihat
    0.90
    ra
    0.89
    ahat
    0.89
    akat
    0.89
    awat
    0.88
    Act Density 0.076%

    No Known Activations