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

    Neuronpedia

    INDEX
    Explanations

    Present value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nors
    -0.07
    petition
    -0.06
    貸
    -0.06
    هم
    -0.06
    oving
    -0.06
    賽
    -0.06
    탈
    -0.06
     Winners
    -0.06
    _Click
    -0.06
    نع
    -0.06
    POSITIVE LOGITS
    (bar
    0.07
    46
    0.06
    SJ
    0.06
     AVL
    0.06
     всп
    0.06
    ə
    0.06
     yerini
    0.06
    ottie
    0.06
     같은
    0.06
     vertices
    0.06
    Act Density 0.011%

    No Known Activations