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

    Neuronpedia

    INDEX
    Explanations

    Hebrew words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Expanded
    0.42
     えっ
    0.39
    expanded
    0.37
     ዕ
    0.35
     patriots
    0.35
    še
    0.34
     अप्र
    0.34
     ім
    0.34
    Expanded
    0.34
    dessä
    0.34
    POSITIVE LOGITS
     justific
    0.39
    GS
    0.37
    igail
    0.37
    })/
    0.37
    zul
    0.37
    noise
    0.37
    Balls
    0.37
     scoping
    0.37
     wai
    0.36
     distancia
    0.36
    Act Density 0.002%

    No Known Activations