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

    Neuronpedia

    INDEX
    Explanations

    repeating characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    баров
    0.38
    બે
    0.37
     cohom
    0.37
     Revelation
    0.37
    ρού
    0.36
    த்தோ
    0.36
    клары
    0.35
    свя
    0.35
     liés
    0.35
     conjoint
    0.35
    POSITIVE LOGITS
    iiii
    0.42
    ssss
    0.41
    etc
    0.40
    ffffff
    0.38
    >>>
    0.37
    ـــ
    0.37
    aaaaaaaa
    0.37
    ০০০
    0.36
    uuuu
    0.36
    hhhh
    0.36
    Act Density 0.011%

    No Known Activations