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

    Neuronpedia

    INDEX
    Explanations

    running python or rust scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     humanist
    0.88
     HubSpot
    0.83
     Perseverance
    0.83
     Scrum
    0.82
     conceptions
    0.82
     Kaufmann
    0.81
     aspirant
    0.81
     Prep
    0.80
     Magento
    0.80
     Treating
    0.79
    POSITIVE LOGITS
    localObject
    1.08
    Anonymous
    1.07
    Synthetic
    0.91
    Parcel
    0.91
    MethodBeat
    0.90
    zzi
    0.85
    arrayList
    0.84
    FUNC
    0.83
    zza
    0.82
     localObject
    0.81
    Act Density 0.006%

    No Known Activations