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

    Neuronpedia

    INDEX
    Explanations

    built Dun & Bradstreet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     palabras
    0.43
     Séance
    0.42
    zó
    0.42
     alrededor
    0.41
     Sud
    0.40
    Sud
    0.40
     aliases
    0.40
    kum
    0.39
     topik
    0.39
    rück
    0.39
    POSITIVE LOGITS
    を経
    0.41
    是一家
    0.39
    asibility
    0.37
    滕
    0.36
     የሆነ
    0.36
    ቨ
    0.35
     firm
    0.35
     በፍ
    0.35
    儅
    0.35
    ፈል
    0.35
    Act Density 0.000%

    No Known Activations