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

    Neuronpedia

    INDEX
    Explanations

    advance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     及
    -0.07
    受
    -0.07
    iedo
    -0.06
    πι
    -0.06
     쉽
    -0.06
    loomberg
    -0.06
    ters
    -0.06
    -même
    -0.06
    -leg
    -0.06
    Dos
    -0.06
    POSITIVE LOGITS
    (stderr
    0.07
    ])->
    0.06
     Skill
    0.06
     radiation
    0.06
    /cl
    0.06
     automotive
    0.06
    ,-
    0.06
    (cl
    0.06
     mekan
    0.06
     �
    0.06
    Act Density 0.021%

    No Known Activations