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

    Neuronpedia

    INDEX
    Explanations

    distance from places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вокруг
    0.63
     mante
    0.62
     gedacht
    0.59
     débil
    0.58
    ン
    0.57
    Ги
    0.55
    ᙱ
    0.55
     involunt
    0.54
     inconsider
    0.54
     indistinct
    0.54
    POSITIVE LOGITS
    the
    0.64
    have
    0.64
     the
    0.58
    Polic
    0.57
    farmers
    0.56
    Slice
    0.55
    of
    0.54
    utm
    0.54
    1
    0.54
     County
    0.53
    Act Density 0.001%

    No Known Activations