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

    Neuronpedia

    INDEX
    Explanations

    formal legal and administrative terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heuristics
    0.94
     tweaks
    0.93
     دچار
    0.93
     tweaking
    0.92
     ficción
    0.91
     နဲ့
    0.91
     fascinated
    0.90
     newbies
    0.89
     특징
    0.89
    weird
    0.89
    POSITIVE LOGITS
     pursuant
    1.94
     pending
    1.52
     Pursuant
    1.50
     subject
    1.40
     conformément
    1.40
     commencing
    1.38
     upon
    1.37
     under
    1.33
     forthwith
    1.26
    subject
    1.23
    Act Density 0.865%

    No Known Activations