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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    kur
    -0.06
    -
↵
    -0.06
     highlight
    -0.06
    CUS
    -0.06
    ůž
    -0.06
     Gareth
    -0.06
    EAR
    -0.06
    Evaluation
    -0.06
    Buff
    -0.06
    POSITIVE LOGITS
     предостав
    0.07
    film
    0.07
     autorelease
    0.07
     traveller
    0.07
     文件
    0.07
     آلمان
    0.06
    ублі
    0.06
    _challenge
    0.06
     vaše
    0.06
    OfBirth
    0.06
    Act Density 0.008%

    No Known Activations