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

    Neuronpedia

    INDEX
    Explanations

    requires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wanted
    0.78
    wanted
    0.76
     যেন
    0.71
    iende
    0.68
     جبر
    0.67
     जुटा
    0.66
     आलम
    0.66
     olsun
    0.65
    ckt
    0.64
    终于
    0.64
    POSITIVE LOGITS
     requires
    3.59
     require
    3.49
     requiring
    3.22
     Requires
    3.18
    requires
    3.15
    require
    3.13
    Requires
    3.13
     Require
    3.06
     requiere
    2.96
    Require
    2.82
    Act Density 0.423%

    No Known Activations