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

    Neuronpedia

    INDEX
    Explanations

    common and frustrating problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     timeless
    0.98
     why
    0.91
     enjoyable
    0.87
     pourquoi
    0.86
     pleasurable
    0.85
    為什麼
    0.85
     toekomst
    0.84
     biodivers
    0.81
     waarom
    0.80
     joyful
    0.80
    POSITIVE LOGITS
     indicating
    0.87
    indicating
    0.82
     vermutlich
    0.82
     möglicherweise
    0.78
    либо
    0.77
    Unable
    0.75
    стран
    0.72
    典型的
    0.71
    もしくは
    0.71
    presumably
    0.71
    Act Density 0.052%

    No Known Activations