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
    AKE
    -0.06
     Facilities
    -0.06
     Studio
    -0.06
    _gender
    -0.06
    ocio
    -0.06
    ORB
    -0.06
    有效
    -0.06
     Glouce
    -0.06
     Brigham
    -0.06
     triplet
    -0.06
    POSITIVE LOGITS
     PP
    0.07
    acea
    0.06
    폴
    0.06
     Ngân
    0.06
    (contact
    0.06
    ア
    0.06
    .contacts
    0.06
    shore
    0.06
     ;↵
    0.06
    fetchAll
    0.06
    Act Density 0.095%

    No Known Activations