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

    Neuronpedia

    INDEX
    Explanations

    citations with et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hover
    0.56
     inad
    0.54
     ->
    0.53
     hovering
    0.52
    ->
    0.51
    overflow
    0.50
     '+'
    0.50
     Obviously
    0.49
     obvious
    0.49
     fallback
    0.49
    POSITIVE LOGITS
     et
    1.56
     eds
    1.47
    等人
    1.17
     unpublished
    1.12
     editors
    1.12
     Eds
    1.11
     citado
    1.10
     एट
    1.09
     publicado
    1.06
    etal
    1.05
    Act Density 0.040%

    No Known Activations