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

    Neuronpedia

    INDEX
    Explanations

    first and square sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abhor
    0.37
     agrad
    0.36
     கொடு
    0.36
     поко
    0.35
     үшін
    0.35
    为
    0.35
     Aug
    0.34
     (~
    0.34
     তৎকালীন
    0.34
    為
    0.34
    POSITIVE LOGITS
    樁
    0.43
    araoh
    0.43
    नीचर
    0.43
    projectName
    0.42
     busier
    0.42
    ローブ
    0.42
     समितियों
    0.40
    騾
    0.39
    高齢
    0.39
     collier
    0.39
    Act Density 0.002%

    No Known Activations