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

    Neuronpedia

    INDEX
    Explanations

    emergency numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     detectives
    0.39
    Digits
    0.38
    City
    0.38
    Squad
    0.38
    lap
    0.37
    Overse
    0.37
    Barnes
    0.37
    equival
    0.36
     equivalent
    0.36
    city
    0.36
    POSITIVE LOGITS
     आंतरिक
    0.41
     emargin
    0.40
     MTLTexture
    0.38
     HANDLE
    0.38
     generando
    0.38
     direito
    0.38
     cabelo
    0.38
     Chatt
    0.37
     কল
    0.37
     autora
    0.37
    Act Density 0.007%

    No Known Activations