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

    Neuronpedia

    INDEX
    Explanations

    detailed metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    golden
    0.47
     golden
    0.41
    мах
    0.40
    Golden
    0.36
    𝒈
    0.36
     Golden
    0.35
    íso
    0.35
    ishan
    0.35
    太陽
    0.34
    Michael
    0.34
    POSITIVE LOGITS
     भेट
    0.42
     vuccati
    0.39
     rau
    0.39
    ++)
    0.39
     भीड़
    0.38
    න්ට
    0.38
     panggilan
    0.38
    etku
    0.37
    kprop
    0.37
     صعبه
    0.37
    Act Density 0.001%

    No Known Activations