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

    Neuronpedia

    INDEX
    Explanations

    stems from, based on, runtime scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jar
    0.41
     van
    0.38
     Edwin
    0.37
    elernt
    0.37
     tiz
    0.36
     tini
    0.36
    hab
    0.35
     volt
    0.35
     stripe
    0.35
    nab
    0.35
    POSITIVE LOGITS
    屇
    0.39
    트워크
    0.39
     LAYER
    0.38
     Workers
    0.38
     سوش
    0.37
     microbi
    0.36
     Auswirkungen
    0.36
     Webs
    0.35
    avidin
    0.35
     setData
    0.35
    Act Density 0.001%

    No Known Activations