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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Apartamento
    -0.08
     Só
    -0.08
     Kommune
    -0.08
     Agencia
    -0.08
     bearbeiten
    -0.07
    wani
    -0.07
    texto
    -0.07
     iw
    -0.07
     amag
    -0.07
     agitation
    -0.07
    POSITIVE LOGITS
    ுவர்
    0.08
    ுக
    0.08
    יי�
    0.08
     grosses
    0.07
     gag
    0.07
    یکل
    0.07
    علوم
    0.07
     дад
    0.07
     тро
    0.07
    ಮು
    0.07
    Act Density 0.001%

    No Known Activations