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

    Neuronpedia

    INDEX
    Explanations

    São Paulo, Brazil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     двой
    0.38
     hints
    0.37
    𝚔
    0.35
     shifting
    0.35
    玦
    0.35
    গে
    0.34
     եր
    0.34
     choosing
    0.34
    Snackbar
    0.34
     castles
    0.34
    POSITIVE LOGITS
    Pizza
    0.40
     Paraná
    0.40
     Yaz
    0.40
    名古屋
    0.39
    মুর
    0.39
     Jap
    0.38
     ట్ర
    0.38
     fag
    0.37
    Exper
    0.37
     jap
    0.36
    Act Density 0.005%

    No Known Activations