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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =>'
    -0.08
    才能
    -0.07
     ^.
    -0.07
    浪
    -0.07
     ","
    -0.07
    @endforeach
    -0.07
    การจ
    -0.07
    ("================
    -0.06
    forth
    -0.06
    าระ
    -0.06
    POSITIVE LOGITS
     Complaint
    0.06
     Zombies
    0.06
    .Simple
    0.06
    ILITIES
    0.06
    (Set
    0.05
     Youth
    0.05
    dating
    0.05
    (balance
    0.05
     incur
    0.05
    .xaml
    0.05
    Act Density 0.281%

    No Known Activations