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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     times
    -0.80
     time
    -0.74
     TIMES
    -0.61
    times
    -0.60
    timed
    -0.60
    TIMES
    -0.58
    SequentialGroup
    -0.58
    Times
    -0.57
     now
    -0.56
    ITHUB
    -0.55
    POSITIVE LOGITS
     שוליים
    0.62
     termica
    0.56
     Diſ
    0.55
     AspNetCore
    0.54
     BorderRadius
    0.52
     Theſe
    0.52
     Houſe
    0.52
     généraux
    0.51
     économies
    0.50
    itinéraire
    0.49
    Act Density 0.002%

    No Known Activations