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

    Neuronpedia

    INDEX
    Explanations

    world in Russian quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sovr
    0.41
    multip
    0.41
     thuật
    0.40
     פּ
    0.39
    algorith
    0.38
     Datenbank
    0.38
     गोपनीयता
    0.38
    ких
    0.37
    Grupo
    0.37
    BuildContext
    0.37
    POSITIVE LOGITS
    _
    0.40
     Mobil
    0.39
     mobil
    0.38
     wedge
    0.38
     Chevron
    0.38
    ropolitan
    0.37
    "
    0.37
     core
    0.36
     enabled
    0.36
     hot
    0.36
    Act Density 0.000%

    No Known Activations