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

    Neuronpedia

    INDEX
    Explanations

    allowing yourself / themselves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वर्ती
    0.55
    чени
    0.48
    ahari
    0.47
    कमा
    0.46
    下图
    0.45
    childNodes
    0.45
    شاہ
    0.44
     orthodoxy
    0.44
    োপাধ্যায়
    0.43
     علاقوں
    0.43
    POSITIVE LOGITS
    BI
    0.54
    BL
    0.51
                                  
    0.50
    BD
    0.49
    VO
    0.48
    l
    0.48
    BE
    0.48
     and
    0.46
    be
    0.46
    PI
    0.46
    Act Density 0.004%

    No Known Activations