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

    Neuronpedia

    INDEX
    Explanations

    future and later events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allclasses
    0.75
    noy
    0.70
     ఇచ్చిన
    0.65
    ẳn
    0.65
     көрс
    0.64
    romy
    0.64
     gevolg
    0.63
    ocused
    0.63
    казыва
    0.63
    äsident
    0.63
    POSITIVE LOGITS
     later
    4.51
     future
    3.98
     someday
    3.87
     eventually
    3.79
    later
    3.78
     Later
    3.74
     später
    3.74
    Later
    3.66
     senere
    3.64
    future
    3.44
    Act Density 0.886%

    No Known Activations