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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lista
    -0.07
     мног
    -0.07
    935
    -0.06
     kommt
    -0.06
    해
    -0.06
    utors
    -0.06
    说
    -0.06
    CUDA
    -0.06
    $start
    -0.06
    header
    -0.06
    POSITIVE LOGITS
    _tool
    0.06
    preserve
    0.06
    	Element
    0.06
    ,options
    0.06
    _LICENSE
    0.06
    (remove
    0.06
    μένου
    0.06
    _reward
    0.06
    spr
    0.06
     ورزشی
    0.06
    Act Density 0.036%

    No Known Activations