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

    Neuronpedia

    INDEX
    Explanations

    complex questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    怿
    1.43
    ຫຼື
    1.36
    黢
    1.35
    eOut
    1.33
     Ainda
    1.32
    <unused1206>
    1.30
     rhinophores
    1.29
     quase
    1.28
     trialComponents
    1.28
     nhỉ
    1.24
    POSITIVE LOGITS
    5
    1.11
    ).
    1.08
    The
    1.07
    3
    1.06
     The
    1.05
    9
    1.05
     ۵
    1.05
    B
    1.04
    2
    1.04
    7
    1.03
    Act Density 0.245%

    No Known Activations