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

    Neuronpedia

    INDEX
    Explanations

    list items, bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scalable
    0.36
     generic
    0.35
    0.35
     reliable
    0.33
     kernel
    0.33
    0
    0.32
     optimized
    0.31
     abstract
    0.31
     up
    0.31
     nutshell
    0.31
    POSITIVE LOGITS
     Vestone
    0.40
    aronne
    0.36
     tämän
    0.36
    ेत्र
    0.35
    useum
    0.35
     Yardım
    0.35
     മറ്റു
    0.35
     asesin
    0.35
     다른
    0.33
     Lobkovic
    0.33
    Act Density 0.002%

    No Known Activations