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

    Neuronpedia

    INDEX
    Explanations

    and/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sys
    -0.07
    มหาว
    -0.06
     AssemblyCompany
    -0.06
     Queens
    -0.06
    DEX
    -0.06
     zde
    -0.06
     Height
    -0.06
    デ
    -0.06
     hello
    -0.06
     powerful
    -0.06
    POSITIVE LOGITS
    งข
    0.07
    っと
    0.06
    овор
    0.06
    тал
    0.06
    _ax
    0.06
     (%)
    0.06
    країн
    0.06
     coz
    0.06
     (?,
    0.06
     ศ
    0.06
    Act Density 0.052%

    No Known Activations