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

    Neuronpedia

    INDEX
    Explanations

    use of proceeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.19
    is
    0.83
    and
    0.75
    й
    0.72
     These
    0.71
     They
    0.68
    რც
    0.68
    いき
    0.66
     ব্যবসায়
    0.65
     hostilities
    0.64
    POSITIVE LOGITS
    ات
    0.92
    3
    0.86
    iť
    0.77
    ۳
    0.69
    ٣
    0.69
    ET
    0.67
    INN
    0.67
    at
    0.66
    .³
    0.66
    ៣
    0.66
    Act Density 0.000%

    No Known Activations