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

    Neuronpedia

    INDEX
    Explanations

    taking photos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     both
    2.25
     strategy
    2.05
     on
    1.95
     family
    1.95
     with
    1.93
     along
    1.92
     of
    1.91
     trips
    1.88
     Family
    1.85
     strategies
    1.82
    POSITIVE LOGITS
    rinsic
    2.84
     akademik
    2.49
     кван
    2.38
    gebäude
    2.36
     Kohn
    2.34
    инг
    2.29
    udarstvennyj
    2.28
    ٦
    2.26
     пусто
    2.25
    ٧
    2.24
    Act Density 0.053%

    No Known Activations