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

    Neuronpedia

    INDEX
    Explanations

    events and performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encyclopedia
    0.35
    రిత్ర
    0.34
     ensayo
    0.33
     caring
    0.32
    战争
    0.31
     relato
    0.30
    尔
    0.30
     hermoso
    0.30
     treasure
    0.29
    রির
    0.29
    POSITIVE LOGITS
    pm
    0.39
    pp
    0.39
    with
    0.38
     concerts
    0.38
    in
    0.37
    ad
    0.37
    es
    0.36
     با
    0.36
    هم
    0.36
    events
    0.36
    Act Density 0.070%

    No Known Activations