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

    Neuronpedia

    INDEX
    Explanations

    direct pain point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹁
    0.45
    Assemblies
    0.44
    ماس
    0.44
    Sends
    0.43
    שא
    0.43
     palais
    0.43
    ziak
    0.42
    Matrices
    0.41
    嚧
    0.41
     দিতেন
    0.40
    POSITIVE LOGITS
     for
    0.58
     unresponsive
    0.55
     организа
    0.53
     betterment
    0.53
    ।
    0.52
    ية
    0.52
    né
    0.52
     organiz
    0.52
     human
    0.51
    nce
    0.51
    Act Density 0.000%

    No Known Activations