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

    Neuronpedia

    INDEX
    Explanations

    variable prefixes for common technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    َ
    0.35
    će
    0.34
    LGBT
    0.32
    وني
    0.30
     اہلِ
    0.30
    巉
    0.30
    م
    0.30
    ني
    0.30
    Responsibilities
    0.30
     Greyhound
    0.30
    POSITIVE LOGITS
     manually
    0.35
    _
    0.34
     mutex
    0.31
     leftmost
    0.31
     kullanımı
    0.31
    ized
    0.29
     mechanism
    0.29
     detection
    0.29
     출력
    0.29
     calculation
    0.29
    Act Density 0.073%

    No Known Activations