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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mails
    -0.07
    'B
    -0.06
     }

↵
    -0.06
    inas
    -0.06
    rl
    -0.06
    ertificate
    -0.06
     network
    -0.06
     fighters
    -0.06
     owe
    -0.06
    izados
    -0.06
    POSITIVE LOGITS
     그의
    0.06
    amu
    0.06
    ），
    0.06
    登場
    0.06
    очных
    0.06
    очные
    0.06
     стар
    0.06
     креп
    0.06
    Benefits
    0.06
     DependencyProperty
    0.06
    Act Density 0.001%

    No Known Activations