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

    Neuronpedia

    INDEX
    Explanations

    physical connection or conversation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    all
    0.40
    pel
    0.38
     గొప్ప
    0.38
    ຖືກ
    0.38
     직접
    0.36
     自分
    0.36
     વી
    0.35
     സ്വന്ത
    0.35
    spare
    0.35
     Два
    0.35
    POSITIVE LOGITS
     consulted
    0.45
     consultas
    0.44
     kaj
    0.41
    iatan
    0.40
     konsult
    0.39
     Charles
    0.39
     कांटे
    0.39
    ള്
    0.39
    uhkan
    0.39
     Spokes
    0.38
    Act Density 0.003%

    No Known Activations