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

    Neuronpedia

    INDEX
    Explanations

    numbers and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erkek
    0.36
    PreferredItem
    0.35
     herkes
    0.34
     herkese
    0.34
    akespeare
    0.33
    ायदे
    0.33
     pinturas
    0.32
    পন্ন
    0.32
     prefque
    0.32
    dze
    0.32
    POSITIVE LOGITS
    除了
    0.40
    使用
    0.38
    也會
    0.38
     Registration
    0.37
    тора
    0.37
     Module
    0.36
     Model
    0.36
     MSI
    0.35
     registration
    0.35
     scope
    0.35
    Act Density 0.000%

    No Known Activations