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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     termica
    -0.68
     mennes
    -0.63
     médicale
    -0.59
     marins
    -0.59
     faciles
    -0.59
     semplici
    -0.58
     commerciaux
    -0.57
     a
    -0.57
     nehé
    -0.56
     registrazione
    -0.56
    POSITIVE LOGITS
     spot
    0.71
     AttributeSet
    0.68
     تكبرها
    0.64
     diagnose
    0.63
     handle
    0.63
     getItemId
    0.63
     administer
    0.62
     organise
    0.62
     fieldNum
    0.60
    SharedDtor
    0.60
    Act Density 0.013%

    No Known Activations