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

    Neuronpedia

    INDEX
    Explanations

    analytical, strong, problem-solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     这个
    0.80
    ारा
    0.72
    راف
    0.70
     명이
    0.70
    創業
    0.69
    ifin
    0.69
    ita
    0.69
    这个
    0.68
     이후
    0.68
     তাও
    0.68
    POSITIVE LOGITS
     whol
    0.98
     wholesome
    0.86
     Espí
    0.82
    urón
    0.82
     Nesse
    0.79
    вший
    0.79
     untersucht
    0.78
     deut
    0.77
     auricul
    0.77
    р
    0.77
    Act Density 0.001%

    No Known Activations