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

    Neuronpedia

    INDEX
    Explanations

    National Sexual or Center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.54
     in
    0.48
     Of
    0.43
    ใน
    0.42
     republics
    0.42
     ή
    0.41
    ın
    0.40
     в
    0.39
     σε
    0.39
    т
    0.39
    POSITIVE LOGITS
    in
    0.45
    。
    0.42
    inę
    0.37
    نا
    0.36
    inį
    0.35
    FA
    0.35
    forEach
    0.34
    CH
    0.34
    。"
    0.34
    abhut
    0.34
    Act Density 0.021%

    No Known Activations