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

    Neuronpedia

    INDEX
    Explanations

    high standards, accountability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.59
    ד
    0.59
    iophor
    0.58
     by
    0.58
     promoter
    0.55
    by
    0.51
    ας
    0.50
    infection
    0.50
    ی
    0.49
    y
    0.49
    POSITIVE LOGITS
     Hendricks
    0.60
    隠
    0.57
     pours
    0.55
     Regen
    0.55
     Judd
    0.55
    データを
    0.54
     abundantly
    0.54
     Hendrick
    0.54
     Connell
    0.54
     anbieten
    0.54
    Act Density 0.001%

    No Known Activations