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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '>↵↵
    -0.07
    potential
    -0.07
    ?;↵↵
    -0.07
    」↵↵
    -0.07
    .Fore
    -0.07
     RuntimeObject
    -0.07
    Professor
    -0.06
    (dest
    -0.06
     özel
    -0.06
    Connell
    -0.06
    POSITIVE LOGITS
     đạt
    0.06
    �
    0.06
     Quang
    0.06
    ینگ
    0.06
     graded
    0.06
     Dating
    0.06
     valide
    0.06
    ورن
    0.06
    َي
    0.06
     Supporters
    0.06
    Act Density 0.087%

    No Known Activations