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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ardi
    -0.27
    —that
    -0.27
    pedia
    -0.25
    esda
    -0.25
    ','$
    -0.25
    ',{↵
    -0.24
     sip
    -0.24
    ARDS
    -0.24
    æī£éĻ¤
    -0.24
    ernote
    -0.23
    POSITIVE LOGITS
    :
    0.60
    :t
    0.44
    :<?
    0.42
    :T
    0.42
    :L
    0.40
    :(
    0.40
    :!
    0.39
    :S
    0.38
    ï¼ļ
    0.38
    :B
    0.38
    Act Density 0.004%

    No Known Activations