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

    Neuronpedia

    INDEX
    Explanations

    technical structured lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prohib
    0.47
     avenue
    0.46
     on
    0.45
    STATE
    0.45
     недели
    0.44
    なる
    0.44
    fashioned
    0.44
     утра
    0.44
     it
    0.43
     poses
    0.43
    POSITIVE LOGITS
    繋がりたい
    0.46
     처리
    0.44
     الرئيسي
    0.43
     đáy
    0.43
    处理
    0.43
    處理
    0.42
    账户
    0.41
     vált
    0.41
     চার
    0.41
    παϊ
    0.41
    Act Density 0.000%

    No Known Activations