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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .EqualTo
    -0.07
    به
    -0.06
    mort
    -0.06
    ementia
    -0.06
     vede
    -0.06
    :Register
    -0.06
     halt
    -0.06
    ®,
    -0.06
    imeType
    -0.06
     Hoe
    -0.06
    POSITIVE LOGITS
     desktop
    0.06
     باشگاه
    0.06
     deeper
    0.06
     node
    0.06
     Afghanistan
    0.06
     bindings
    0.06
     اقتصادی
    0.06
     efficacy
    0.06
    coverage
    0.06
     AssemblyCompany
    0.06
    Act Density 0.001%

    No Known Activations