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

    Neuronpedia

    INDEX
    Explanations

    Purchases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DEM
    -0.08
    _runner
    -0.07
    真正做到
    -0.07
     Framework
    -0.07
     medium
    -0.07
    끎
    -0.07
    (ls
    -0.07
    venta
    -0.06
    ชาว
    -0.06
    々
    -0.06
    POSITIVE LOGITS
    .Require
    0.07
     breadcrumbs
    0.07
    emacs
    0.07
     uncle
    0.07
     strange
    0.07
    иск
    0.07
    such
    0.07
    #elif
    0.07
    	elseif
    0.07
    hell
    0.06
    Act Density 0.077%

    No Known Activations