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

    Neuronpedia

    INDEX
    Explanations

    at its core/heart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     중요
    0.82
     notable
    0.73
     특징
    0.72
     important
    0.72
     영향
    0.72
     importance
    0.71
     özellikleri
    0.71
     이유는
    0.71
     interesting
    0.70
     luckily
    0.69
    POSITIVE LOGITS
     heart
    1.36
     corazón
    1.24
     core
    1.21
     root
    1.17
     Heart
    1.17
     Root
    1.14
     at
    1.13
    Heart
    1.13
    root
    1.11
     cuore
    1.10
    Act Density 0.483%

    No Known Activations