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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ğ
    -0.08
    edir
    -0.07
     onSave
    -0.07
    ression
    -0.06
    iid
    -0.06
     Lanc
    -0.06
     M
    -0.06
     marrying
    -0.06
     dow
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Both
    0.09
    both
    0.08
     BOTH
    0.07
    ่าส
    0.06
    skyt
    0.06
    signin
    0.06
    crets
    0.06
    　　　　　　　　　　　　
    0.06
     Cargo
    0.06
    (TEXT
    0.06
    Act Density 0.020%

    No Known Activations