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

    Neuronpedia

    INDEX
    Explanations

    build number settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نتيجة
    0.44
    𒈨
    0.43
    efeuille
    0.43
     erythematosus
    0.42
    sklär
    0.41
     solides
    0.40
    ᵕ
    0.40
     ferrugine
    0.40
     клі
    0.40
    ")%>%
    0.40
    POSITIVE LOGITS
    BuildConfig
    0.67
     BuildConfig
    0.59
     DEBUG
    0.44
     Constants
    0.40
     public
    0.40
     gas
    0.39
     build
    0.38
     Build
    0.38
     hard
    0.38
     builder
    0.38
    Act Density 0.001%

    No Known Activations