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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovariant
    0.42
    िस्थित
    0.38
    ⅳ
    0.36
     분위
    0.36
    いを
    0.36
     እነዚህ
    0.36
     wysokości
    0.36
     규모
    0.36
     graciously
    0.36
     ءِ
    0.35
    POSITIVE LOGITS
     webcam
    0.42
     Webcam
    0.37
     Influ
    0.34
     Prou
    0.33
     unsc
    0.33
     diaphragm
    0.33
     MSD
    0.32
     AutoCAD
    0.32
     கடற்க
    0.32
    Function
    0.31
    Act Density 0.002%

    No Known Activations