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

    Neuronpedia

    INDEX
    Explanations

    After

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    equals
    -0.07
     Some
    -0.07
    YSQL
    -0.07
     впол
    -0.06
     Estr
    -0.06
    dogs
    -0.06
    Machine
    -0.06
     purpose
    -0.06
    Wilson
    -0.06
    γραφή
    -0.06
    POSITIVE LOGITS
    ợi
    0.07
    財
    0.07
    Advertisements
    0.06
     warmly
    0.06
    afen
    0.06
     Tôi
    0.06
    ')"
    0.06
     zeit
    0.06
     Liability
    0.06
    ろ
    0.06
    Act Density 0.022%

    No Known Activations