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

    Neuronpedia

    INDEX
    Explanations

    offering assistance and seeking input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৩৮
    0.87
     famosa
    0.86
    名称
    0.86
    괵
    0.84
    Eine
    0.84
    などに
    0.83
    碖
    0.81
    하였
    0.77
    名稱
    0.76
     famoso
    0.76
    POSITIVE LOGITS
     *
    1.12
     _
    1.10
     OUR
    0.92
     him
    0.84
     최대한
    0.83
     **
    0.83
     thoughtfulness
    0.83
     helping
    0.82
     HIS
    0.82
     YOUR
    0.81
    Act Density 0.576%

    No Known Activations