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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _classifier
    -0.07
     mosque
    -0.07
    /services
    -0.07
     hill
    -0.07
     fever
    -0.07
     maneuvers
    -0.07
    jar
    -0.06
     aktar
    -0.06
    itzer
    -0.06
    administrator
    -0.06
    POSITIVE LOGITS
     Squ
    0.06
    .class
    0.06
    ]^
    0.06
     Because
    0.06
     UK
    0.06
     Fox
    0.06
     จ
    0.06
    Intern
    0.06
     Stores
    0.06
     Ign
    0.06
    Act Density 0.169%

    No Known Activations