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

    Neuronpedia

    INDEX
    Explanations

    Symbolic links and informational content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μού
    0.42
     기타
    0.42
     MAC
    0.40
     UCS
    0.40
    設計
    0.39
     不
    0.39
     вызвать
    0.39
     χρόνο
    0.39
    મી
    0.39
    ell
    0.38
    POSITIVE LOGITS
    '،
    0.48
    🥚
    0.47
     العمليه
    0.45
     grinder
    0.43
    "،
    0.42
     fühlen
    0.41
    ljena
    0.41
    在一个
    0.41
     لذ
    0.41
     bezpiecze
    0.41
    Act Density 0.003%

    No Known Activations