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

    Neuronpedia

    INDEX
    Explanations

    Code and database info

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nun
    -0.08
     repeal
    -0.07
    -interest
    -0.07
     reality
    -0.06
     Teen
    -0.06
    Reality
    -0.06
     manages
    -0.06
    StatusBar
    -0.06
    Friend
    -0.06
    lrt
    -0.06
    POSITIVE LOGITS
    chartInstance
    0.06
    TexParameter
    0.06
    issional
    0.06
     Sb
    0.06
    oglob
    0.06
     hwnd
    0.06
    ../../
    0.06
     avantaj
    0.06
     "{\"
    0.06
     sanat
    0.06
    Act Density 0.047%

    No Known Activations