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

    Neuronpedia

    INDEX
    Explanations

    Bed and Breakfast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.74
    ini
    0.71
    8
    0.69
    ür
    0.64
    ator
    0.64
    OU
    0.64
     हवाला
    0.64
    hi
    0.63
    ill
    0.61
    IO
    0.61
    POSITIVE LOGITS
    is
    0.71
    ת
    0.60
    活動
    0.58
    os
    0.57
    ות
    0.57
     \
    0.56
    活动
    0.55
    变
    0.55
    дение
    0.55
     The
    0.54
    Act Density 0.000%

    No Known Activations