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

    Neuronpedia

    INDEX
    Explanations

    is/was followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trained
    0.72
     কর্মরত
    0.64
     belonging
    0.64
     bred
    0.64
     belong
    0.62
     Trained
    0.61
    ,_
    0.61
     klaar
    0.59
     grown
    0.59
     कार्यरत
    0.59
    POSITIVE LOGITS
     punctuated
    1.61
     interrupted
    1.37
     marred
    1.22
     pepper
    1.13
     attended
    1.10
     followed
    1.10
     dominated
    1.09
     preceded
    1.09
     presided
    1.08
     accompanied
    1.07
    Act Density 0.038%

    No Known Activations