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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    垠
    -0.08
     cms
    -0.07
     חז
    -0.07
    小学
    -0.07
     stressing
    -0.07
    电子商务
    -0.07
    管委会
    -0.06
    叚
    -0.06
     prv
    -0.06
    柠檬
    -0.06
    POSITIVE LOGITS
     queer
    0.07
    œur
    0.07
     Şi
    0.06
    𝆣
    0.06
    Members
    0.06
    죕
    0.06
    ungan
    0.06
    _EXTRA
    0.06
    .return
    0.06
     doen
    0.06
    Act Density 0.001%

    No Known Activations