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

    Neuronpedia

    INDEX
    Explanations

    Vertical lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '}}
    -0.06
    см
    -0.06
    spiracy
    -0.06
    sym
    -0.06
     Floors
    -0.06
    		↵		↵
    -0.06
    fec
    -0.06
    pais
    -0.05
     manten
    -0.05
    leg
    -0.05
    POSITIVE LOGITS
     opcion
    0.07
     brat
    0.07
     private
    0.07
     Transcript
    0.07
     adjud
    0.07
     solitary
    0.07
    ycz
    0.06
    NTAX
    0.06
     Glob
    0.06
    .append
    0.06
    Act Density 0.006%

    No Known Activations