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

    Neuronpedia

    INDEX
    Explanations

    expansion and policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attualmente
    0.96
     აქვს
    0.95
     हैं
    0.88
     derzeit
    0.84
     Currently
    0.84
     currently
    0.83
     możesz
    0.83
     může
    0.82
     현재
    0.81
     বর্তমানে
    0.81
    POSITIVE LOGITS
    當時
    1.54
     damal
    1.35
     damals
    1.34
     buvo
    1.30
    当时
    1.27
     ήταν
    1.27
    多かった
    1.27
     بودند
    1.21
     étaient
    1.19
     vardı
    1.19
    Act Density 0.372%

    No Known Activations