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

    Neuronpedia

    INDEX
    Explanations

    likely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    likely
    -1.28
     likely
    -1.24
     Likely
    -1.10
    Likely
    -0.96
    GEBURTSDATUM
    -0.82
     StatefulWidget
    -0.71
     unlikely
    -0.67
     LIK
    -0.67
    unlikely
    -0.65
     Probably
    -0.64
    POSITIVE LOGITS
     inaugurated
    0.50
     deported
    0.49
     betweenstory
    0.49
     adul
    0.48
     motivate
    0.47
     evolu
    0.47
     classific
    0.47
     modulated
    0.47
     civi
    0.46
     школу
    0.46
    Act Density 0.056%

    No Known Activations