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

    Neuronpedia

    INDEX
    Explanations

    "Caught in" Middle Managers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    宒
    0.45
    quint
    0.43
     കഴിഞ്ഞ
    0.42
    icots
    0.42
    icot
    0.41
    helm
    0.40
    oleans
    0.40
    ))}{
    0.40
    amanam
    0.39
    ctions
    0.39
    POSITIVE LOGITS
     ''.
    0.39
     ulo
    0.39
     "^
    0.38
     Basin
    0.38
     Coordinator
    0.36
     Stru
    0.36
     States
    0.36
     Stand
    0.36
     WD
    0.36
    ᴗ
    0.36
    Act Density 0.000%

    No Known Activations