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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     largest
    -0.57
     widest
    -0.49
     upcoming
    -0.48
     aforementioned
    -0.48
     final
    -0.48
     highest
    -0.48
     right
    -0.47
     longest
    -0.47
     biggest
    -0.46
     finest
    -0.46
    POSITIVE LOGITS
    tanleria
    0.84
    fromnode
    0.71
     vérit
    0.69
    oredCriteria
    0.68
    UnusedPrivate
    0.66
     ​​
    0.65
    rungsseite
    0.64
     bepaalde
    0.63
     stället
    0.63
     angeles
    0.62
    Act Density 0.009%

    No Known Activations