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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antd
    -0.07
     establishes
    -0.07
     Sans
    -0.07
    arters
    -0.07
     drainage
    -0.06
    eker
    -0.06
    usahaan
    -0.06
    URRED
    -0.06
    forcing
    -0.06
    оре
    -0.06
    POSITIVE LOGITS
    [label
    0.07
     DIN
    0.07
     ειδ
    0.07
    appropriate
    0.06
    　　　　　　　　　　　
    0.06
     Paid
    0.06
    Official
    0.06
     intermitt
    0.06
     발
    0.06
     Essay
    0.06
    Act Density 0.000%

    No Known Activations