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

    Neuronpedia

    INDEX
    Explanations

    stronger than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kana
    0.46
    CustomerID
    0.45
    Celltype
    0.45
    Duz
    0.45
    ොර
    0.44
    dech
    0.44
    CTOGRAM
    0.44
     Perg
    0.44
    ত্তম
    0.43
    Tart
    0.43
    POSITIVE LOGITS
     slumped
    0.49
    quo
    0.47
     stressed
    0.47
     rallied
    0.46
     có
    0.45
    of
    0.45
     pledged
    0.45
     thicker
    0.44
    infected
    0.44
    infl
    0.43
    Act Density 0.000%

    No Known Activations