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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vícti
    -0.76
    trường
    -0.62
     néz
    -0.62
    them
    -0.61
    теризу
    -0.58
     őket
    -0.58
     établi
    -0.57
    Geplaatst
    -0.57
     nødvendig
    -0.56
    yaitu
    -0.56
    POSITIVE LOGITS
     we
    1.07
     you
    0.81
     I
    0.65
    findpost
    0.58
     WE
    0.55
     We
    0.54
     nous
    0.52
     tartalomajánló
    0.51
     Biophys
    0.50
     our
    0.50
    Act Density 0.026%

    No Known Activations