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

    Neuronpedia

    INDEX
    Explanations

    models response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iTunes
    0.44
     Enumer
    0.44
     liggen
    0.43
     Advisory
    0.38
     prezent
    0.38
    Double
    0.38
    zeugt
    0.38
    ทย
    0.37
     Gallo
    0.37
    PPPP
    0.37
    POSITIVE LOGITS
    鉑
    0.36
     endonuclease
    0.35
     चैलेंज
    0.35
    pendicular
    0.35
     grotesque
    0.35
    प्ति
    0.35
    ओके
    0.35
     Bie
    0.35
    մ
    0.35
    mare
    0.34
    Act Density 0.004%

    No Known Activations