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

    Neuronpedia

    INDEX
    Explanations

    suite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “As
    -0.07
    _lookup
    -0.07
    üsü
    -0.06
    /export
    -0.06
    뼉
    -0.06
    ้ง
    -0.06
    .undefined
    -0.06
    /load
    -0.06
     restarted
    -0.06
    _OCCURRED
    -0.06
    POSITIVE LOGITS
     rout
    0.08
    적으로
    0.08
     explorer
    0.07
    	va
    0.07
    thermal
    0.07
    を求め
    0.07
    inqu
    0.07
    ら
    0.07
    -beta
    0.07
    是不会
    0.07
    Act Density 0.004%

    No Known Activations