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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     century
    -0.08
    nten
    -0.07
    .vstack
    -0.07
     Spect
    -0.07
     duty
    -0.07
    licherweise
    -0.07
    Sobre
    -0.07
     বাক
    -0.07
     entendimento
    -0.07
    Spect
    -0.07
    POSITIVE LOGITS
     Montréal
    0.09
    onium
    0.08
    emun
    0.08
     reflector
    0.08
    /he
    0.07
    edges
    0.07
     Montreal
    0.07
     supérieure
    0.07
     inhabitants
    0.07
     брауз
    0.07
    Act Density 0.003%

    No Known Activations