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

    Neuronpedia

    INDEX
    Explanations

    Mathematical computations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {↵
    -0.08
    render
    -0.08
     koristiti
    -0.07
     NEW
    -0.07
     rende
    -0.07
    ':↵
    -0.07
     bruker
    -0.07
     {↵↵
    -0.07
     CURRENT
    -0.07
     render
    -0.07
    POSITIVE LOGITS
     apesar
    0.09
     again
    0.09
     있으
    0.09
     despite
    0.08
     bulun
    0.08
    こちら
    0.08
     unavoidable
    0.08
     awkward
    0.08
     zwar
    0.08
     unh
    0.08
    Act Density 0.016%

    No Known Activations