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

    Neuronpedia

    INDEX
    Explanations

    empathy clarification listening validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stdout
    0.72
    뷁
    0.68
    绘制
    0.68
     সম্পাদকীয়
    0.65
    COMDAT
    0.65
     computationally
    0.63
     outcrops
    0.63
     MNIST
    0.63
    etrotters
    0.62
     rezat
    0.62
    POSITIVE LOGITS
     empath
    1.21
     empat
    1.13
     empathy
    1.09
     Listening
    1.08
     LISTEN
    1.08
     empathetic
    1.07
     listening
    1.03
     probe
    1.02
     phrases
    1.02
     genu
    1.02
    Act Density 0.687%

    No Known Activations