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

    Neuronpedia

    INDEX
    Explanations

    future actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ди
    0.40
    Ва
    0.39
    乚
    0.38
    Ру
    0.37
    Ме
    0.37
    Де
    0.37
    Ха
    0.36
    Degrees
    0.36
    ாகி
    0.36
     অবিশ্বাস্য
    0.36
    POSITIVE LOGITS
     enquire
    0.60
     learnt
    0.55
     got
    0.54
     upto
    0.54
     atleast
    0.54
     irrespective
    0.51
     indulge
    0.50
     mention
    0.50
     have
    0.48
     keep
    0.47
    Act Density 0.003%

    No Known Activations