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

    Neuronpedia

    INDEX
    Explanations

    titles starting with Sir

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \\..
    0.45
    檔
    0.42
    បែ
    0.42
     SSm
    0.41
    岷
    0.41
    Მ
    0.41
    槨
    0.41
     Pei
    0.40
     провер
    0.39
    ParamNum
    0.39
    POSITIVE LOGITS
     sir
    0.69
    Sir
    0.64
     coping
    0.61
     Sir
    0.58
     mechanisms
    0.56
     cope
    0.54
     mechanism
    0.53
     механиз
    0.51
    sir
    0.50
     Mechanism
    0.50
    Act Density 0.004%

    No Known Activations