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

    Neuronpedia

    INDEX
    Explanations

    places and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diagn
    0.49
     DLL
    0.49
     applic
    0.47
     Elekt
    0.47
     Elektro
    0.47
    .
    0.46
     talked
    0.45
     електро
    0.45
     elektro
    0.44
     diagn
    0.43
    POSITIVE LOGITS
    siswa
    0.59
    Typical
    0.54
    ORIG
    0.52
    typical
    0.50
     ज्यादातर
    0.50
    decrease
    0.49
    zhou
    0.48
    𒌑
    0.47
    lou
    0.47
    tao
    0.47
    Act Density 0.004%

    No Known Activations