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

    Neuronpedia

    INDEX
    Explanations

    healthcare, voltage, California

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Statistic
    0.55
    überküloz
    0.55
    Parameter
    0.51
    überkü
    0.49
    Status
    0.49
    Kt
    0.48
    Deletion
    0.47
     生命周期函数
    0.46
    Func
    0.46
    AreaData
    0.45
    POSITIVE LOGITS
     not
    0.54
     I
    0.52
     Some
    0.52
     Our
    0.47
     conci
    0.47
     Ive
    0.46
     München
    0.45
     Yep
    0.44
     tổ
    0.44
     exempel
    0.44
    Act Density 0.024%

    No Known Activations