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

    Neuronpedia

    INDEX
    Explanations

    statistics and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     university
    -0.07
    _TOKEN
    -0.07
    xDF
    -0.06
     Len
    -0.06
     Significant
    -0.06
     contradict
    -0.06
    _swap
    -0.06
    Tree
    -0.06
    REDIT
    -0.06
     Levin
    -0.06
    POSITIVE LOGITS
    'on
    0.06
     expensive
    0.06
    аліст
    0.06
    ifestyles
    0.06
    lt
    0.06
    calloc
    0.06
     здоров
    0.06
     notebook
    0.06
    اشة
    0.06
    /create
    0.06
    Act Density 0.006%

    No Known Activations