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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Customs
    -0.08
     boarded
    -0.06
     Orders
    -0.06
     noises
    -0.06
     floor
    -0.06
     scoff
    -0.06
     exclusive
    -0.06
     wealthy
    -0.06
    Histogram
    -0.06
    _testing
    -0.06
    POSITIVE LOGITS
    `s
    0.06
     Harm
    0.06
    CRE
    0.06
    controlled
    0.06
    三
    0.06
    concert
    0.06
    rPid
    0.06
     debacle
    0.06
    Bir
    0.06
    shima
    0.06
    Act Density 0.004%

    No Known Activations