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

    Neuronpedia

    INDEX
    Explanations

    os.environ get calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🕷
    0.38
     commencer
    0.38
    を開始
    0.36
    𝙔
    0.36
    ीण
    0.34
    ARKS
    0.34
    存档备份
    0.34
    ciparum
    0.34
    զ
    0.34
    станти
    0.33
    POSITIVE LOGITS
    kor
    0.37
    ***
    0.36
     environ
    0.36
     Kor
    0.36
     envi
    0.36
    pro
    0.35
     os
    0.35
    ↵
    0.35
     los
    0.35
     Kore
    0.35
    Act Density 0.000%

    No Known Activations