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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nueva
    -0.07
     thrive
    -0.06
    (Service
    -0.06
    讨
    -0.06
     varios
    -0.06
    (change
    -0.06
     оці
    -0.06
     skies
    -0.06
    야
    -0.06
    Warehouse
    -0.06
    POSITIVE LOGITS
    Asset
    0.07
     Bl
    0.07
     regulates
    0.07
    ellij
    0.07
     tweeting
    0.07
     Cass
    0.07
     图
    0.06
    References
    0.06
    .assertIs
    0.06
     батьків
    0.06
    Act Density 0.012%

    No Known Activations