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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cap
    -0.07
    Craig
    -0.07
     SSC
    -0.07
    _TER
    -0.07
    .adjust
    -0.06
     Craig
    -0.06
    andes
    -0.06
    *scale
    -0.06
     covered
    -0.06
     activated
    -0.06
    POSITIVE LOGITS
     ανα
    0.07
     compliments
    0.06
    lico
    0.06
     查看
    0.06
     investing
    0.06
    aticon
    0.06
     etti
    0.06
     Oracle
    0.06
    *)↵↵
    0.06
     MG
    0.06
    Act Density 0.005%

    No Known Activations