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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objetos
    -0.07
    looks
    -0.07
    lis
    -0.06
     enf
    -0.06
     goats
    -0.06
    -eff
    -0.06
     bullshit
    -0.06
    งน
    -0.06
    Factor
    -0.06
    ibt
    -0.06
    POSITIVE LOGITS
     **↵
    0.07
     visited
    0.06
     Mes
    0.06
     Vog
    0.06
    慢
    0.06
     except
    0.06
     澳
    0.06
     Dream
    0.06
     thumbnail
    0.06
    .setHorizontalAlignment
    0.06
    Act Density 0.010%

    No Known Activations