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

    Neuronpedia

    INDEX
    Explanations

    payments and taxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xfd
    -0.06
    .numpy
    -0.06
     Tennis
    -0.06
     Transportation
    -0.06
    空间
    -0.06
     phishing
    -0.06
     М
    -0.06
     شده
    -0.06
    跑
    -0.06
     amazed
    -0.06
    POSITIVE LOGITS
    _nome
    0.07
     Ül
    0.06
    udit
    0.06
     bestowed
    0.06
     genu
    0.06
     rid
    0.06
    _decrypt
    0.06
     genital
    0.06
    のか
    0.06
     حديث
    0.06
    Act Density 0.030%

    No Known Activations