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

    Neuronpedia

    INDEX
    Explanations

    internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LAG
    -0.28
    -edge
    -0.28
    ataka
    -0.28
    å®ĥåı¯ä»¥
    -0.28
    Upgrade
    -0.27
    è¾¹ç¼ĺ
    -0.26
     Upgrade
    -0.26
     Restricted
    -0.24
    æĬ¼
    -0.24
    رش
    -0.24
    POSITIVE LOGITS
    forces
    0.28
    èĥĨåĽºéĨĩ
    0.27
    azio
    0.27
    .ml
    0.26
    æ§
    0.25
     indonesia
    0.25
    åIJįæł¡
    0.25
     IDS
    0.25
    ouv
    0.25
    ä¾ĽéľĢ
    0.24
    Act Density 0.041%

    No Known Activations