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

    Neuronpedia

    INDEX
    Explanations

    Informal writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unten
    -0.07
    Africa
    -0.07
     rio
    -0.06
    .ping
    -0.06
     UNITY
    -0.06
    _dict
    -0.06
    -legged
    -0.06
     Kang
    -0.06
     Hungarian
    -0.06
     fly
    -0.06
    POSITIVE LOGITS
     прич
    0.07
     jinak
    0.06
    _FM
    0.06
    شناسی
    0.06
     الج
    0.06
    災
    0.06
    �
    0.06
     �
    0.06
     
↵ 
↵
    0.06
    _TRI
    0.06
    Act Density 0.001%

    No Known Activations