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

    Neuronpedia

    INDEX
    Explanations

    opor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tongue
    -0.07
     lw
    -0.07
     oversh
    -0.07
    .Row
    -0.06
    舰
    -0.06
     palms
    -0.06
     Kah
    -0.06
    >a
    -0.06
     saver
    -0.06
    bou
    -0.06
    POSITIVE LOGITS
    opor
    0.09
    ОН
    0.08
    原因
    0.07
     Breaking
    0.07
     이유
    0.07
     milyon
    0.07
    ('/')↵
    0.07
     ($)
    0.06
    ("----------------
    0.06
     ***/↵
    0.06
    Act Density 0.004%

    No Known Activations