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

    Neuronpedia

    INDEX
    Explanations

    code snippets and uncommon text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nights
    -0.07
    Plot
    -0.07
     уч
    -0.06
    (symbol
    -0.06
    Bean
    -0.06
     webhook
    -0.06
    ´t
    -0.06
    _PLAYER
    -0.06
     обо
    -0.06
     Crus
    -0.06
    POSITIVE LOGITS
    Henry
    0.07
     vüc
    0.07
     프랑스
    0.07
     getopt
    0.06
    /testing
    0.06
     JPanel
    0.06
    oga
    0.06
     کیل
    0.06
     Henry
    0.06
    BAR
    0.06
    Act Density 0.000%

    No Known Activations