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

    Neuronpedia

    INDEX
    Explanations

    struggle with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGRAPHY
    0.41
    ਤੀ
    0.40
     একখানি
    0.39
    mercial
    0.38
    образова
    0.38
    footage
    0.38
    coupling
    0.38
    ুমার
    0.38
    simply
    0.36
    obje
    0.36
    POSITIVE LOGITS
     سایر
    0.50
     větš
    0.50
     Otros
    0.47
     diğer
    0.46
     większość
    0.46
     zuverläss
    0.44
     reliably
    0.43
     остальные
    0.43
     reliable
    0.42
     Những
    0.42
    Act Density 0.021%

    No Known Activations