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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cat
    -0.07
    Appointment
    -0.07
    _Frame
    -0.06
    damn
    -0.06
    องจาก
    -0.06
    فق
    -0.06
     будуть
    -0.06
     Exhib
    -0.06
     stoi
    -0.06
    структор
    -0.06
    POSITIVE LOGITS
    Rated
    0.06
     jus
    0.06
    ="'.$
    0.06
    _quotes
    0.06
     gluten
    0.05
     jong
    0.05
    Genesis
    0.05
    ご
    0.05
    Twitter
    0.05
    [href
    0.05
    Act Density 0.003%

    No Known Activations