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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rnn
    -0.06
    (Some
    -0.06
    URLConnection
    -0.06
     Members
    -0.06
     polít
    -0.06
     conexao
    -0.06
    rollers
    -0.06
    aware
    -0.06
    ClientRect
    -0.06
     queens
    -0.06
    POSITIVE LOGITS
    有的
    0.07
     cest
    0.06
     дослідження
    0.06
    。",↵
    0.06
     м
    0.06
     appropriations
    0.06
     пред
    0.06
     मत
    0.06
     línea
    0.06
    508
    0.06
    Act Density 0.012%

    No Known Activations