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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ijn
    -0.07
     Nicaragua
    -0.06
     پیام
    -0.06
    (original
    -0.06
     enraged
    -0.06
    た
    -0.06
    _real
    -0.06
    (effect
    -0.06
    仕事
    -0.06
    Banner
    -0.06
    POSITIVE LOGITS
     PQ
    0.07
    數
    0.07
    але
    0.07
     succeed
    0.06
     Seek
    0.06
     Jo
    0.06
    ATES
    0.06
    技
    0.06
    _queues
    0.06
     sheets
    0.06
    Act Density 0.115%

    No Known Activations