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

    Neuronpedia

    INDEX
    Explanations

    BEST or ERROR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     under
    0.92
    interested
    0.86
     interested
    0.84
     Interested
    0.81
    under
    0.77
     Under
    0.75
    heden
    0.74
    hews
    0.73
    enden
    0.69
     sotto
    0.68
    POSITIVE LOGITS
     což
    0.86
    的存在
    0.83
    大脑
    0.82
    ITEM
    0.81
     मस्तिष्क
    0.79
     pembuatan
    0.77
     !(
    0.77
    platinum
    0.77
     बनेगा
    0.77
    防疫
    0.76
    Act Density 0.000%

    No Known Activations