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

    Neuronpedia

    INDEX
    Explanations

    code/text files/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lcm
    -0.08
     suger
    -0.07
    .from
    -0.07
     cập
    -0.07
    xCB
    -0.07
    psych
    -0.07
    bff
    -0.06
    φέρει
    -0.06
    ]={
    -0.06
    amat
    -0.06
    POSITIVE LOGITS
     Mast
    0.06
     Sing
    0.06
    okay
    0.06
    .Secret
    0.06
    40
    0.06
     sing
    0.06
     필요한
    0.06
     Minimum
    0.06
     node
    0.06
     게시물
    0.05
    Act Density 0.000%

    No Known Activations