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

    Neuronpedia

    INDEX
    Explanations

    structure it into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.31
    au
    1.27
    </td>
    1.20
    AL
    1.19
    isi
    1.16
    П
    1.15
    age
    1.14
    ara
    1.13
    н
    1.13
    원
    1.13
    POSITIVE LOGITS
     quadrants
    1.29
     anodic
    1.26
     structured
    1.22
     organizes
    1.22
     organized
    1.21
     applause
    1.21
    ให้กับ
    1.21
     flowchart
    1.20
     unrivalled
    1.20
     curtailed
    1.19
    Act Density 0.379%

    No Known Activations