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

    Neuronpedia

    INDEX
    Explanations

    dialogue snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inventor
    -0.07
    Writer
    -0.06
     sanitation
    -0.06
     creators
    -0.06
     Communication
    -0.06
     youngster
    -0.06
    ̆
    -0.06
    绩
    -0.06
    ウィ
    -0.06
     인증
    -0.06
    POSITIVE LOGITS
     StObject
    0.06
     pozem
    0.06
    Parsed
    0.06
     dik
    0.06
     möchten
    0.06
     한
    0.06
     Влади
    0.06
    벨
    0.06
    did
    0.06
    _GenericClass
    0.06
    Act Density 0.069%

    No Known Activations