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

    Neuronpedia

    INDEX
    Explanations

    Prisons and recidivism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aşağıd
    -0.07
     deficiency
    -0.07
     Clerk
    -0.07
    ência
    -0.07
     craving
    -0.07
     muscles
    -0.07
     mechanics
    -0.07
    ]<
    -0.06
     <=>
    -0.06
     скоро
    -0.06
    POSITIVE LOGITS
    尊敬
    0.08
     البعض
    0.08
    /navbar
    0.08
     Nixon
    0.07
    thè
    0.07
    apist
    0.07
    (topic
    0.07
    相较于
    0.07
    änn
    0.07
    _OUTPUT
    0.07
    Act Density 0.042%

    No Known Activations