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

    Neuronpedia

    INDEX
    Explanations

    room quality, type, options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.56
    :
    0.55
    다
    0.50
    タ
    0.47
    रा
    0.45
    і
    0.43
    น
    0.42
    ता
    0.41
    نا
    0.41
    기
    0.41
    POSITIVE LOGITS
    c
    0.45
     sevi
    0.39
    asen
    0.38
     dute
    0.38
    𝟎
    0.38
    ç
    0.37
     seroton
    0.37
     Zijn
    0.37
     vitamina
    0.37
     nisk
    0.37
    Act Density 0.000%

    No Known Activations