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

    Neuronpedia

    INDEX
    Explanations

    numpy random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immersive
    0.48
     Kubernetes
    0.47
     intrins
    0.47
     phishing
    0.46
     composed
    0.44
     configure
    0.44
     prosa
    0.43
     using
    0.42
     database
    0.42
     interoper
    0.42
    POSITIVE LOGITS
    obranch
    0.38
    älfte
    0.37
    asjonen
    0.37
    lägg
    0.36
    valueOf
    0.36
    akhir
    0.36
    omen
    0.36
    ionat
    0.36
    arcía
    0.36
     isti
    0.35
    Act Density 0.361%

    No Known Activations