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

    Neuronpedia

    INDEX
    Explanations

    quoted/catalog names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isoform
    0.60
     minimalistic
    0.57
     minimalism
    0.54
     EGFR
    0.54
     backstory
    0.52
     physicality
    0.52
     isoforms
    0.51
     במהלך
    0.50
     densément
    0.50
     cardinality
    0.50
    POSITIVE LOGITS
     SPECIAL
    0.70
     bargains
    0.61
     Genuine
    0.61
    special
    0.59
    SPECIAL
    0.59
     finest
    0.59
     postpaid
    0.58
    strictly
    0.58
     Special
    0.57
     Electric
    0.57
    Act Density 0.002%

    No Known Activations