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

    Neuronpedia

    INDEX
    Explanations

    my or our followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hình
    0.47
    ạc
    0.45
    ərb
    0.45
    높
    0.44
    Alo
    0.43
    ᓲ
    0.43
    tìm
    0.43
    ilibus
    0.43
    구
    0.43
    ⓓ
    0.42
    POSITIVE LOGITS
     Turned
    0.44
     »,
    0.40
     😊
    0.40
     Suite
    0.39
     धमाकेदार
    0.39
     Jr
    0.38
    lite
    0.38
    dings
    0.38
     Systems
    0.38
     Studio
    0.37
    Act Density 0.001%

    No Known Activations