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

    Neuronpedia

    INDEX
    Explanations

    cd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뛴
    -0.07
     compan
    -0.07
     HeaderComponent
    -0.07
    毕竟是
    -0.07
     منتخب
    -0.07
    �
    -0.07
    umbed
    -0.07
     yaşayan
    -0.07
    .NoSuch
    -0.07
     Azerbaijan
    -0.07
    POSITIVE LOGITS
    ез
    0.08
    ò
    0.08
    𝕚
    0.08
     KL
    0.07
    ego
    0.07
     Gel
    0.07
    ap
    0.07
     lp
    0.07
    lass
    0.07
    crawler
    0.07
    Act Density 0.031%

    No Known Activations