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

    Neuronpedia

    INDEX
    Explanations

    hollow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🚗
    -0.08
    asdf
    -0.08
     Jing
    -0.07
     질문
    -0.07
     di
    -0.07
    相聚
    -0.07
    efd
    -0.07
    rodu
    -0.07
     내가
    -0.07
    /*******************************************************************************↵
    -0.07
    POSITIVE LOGITS
     hollow
    0.09
     nobody
    0.07
     Ra
    0.07
    华夏
    0.07
    ある程度
    0.06
    uids
    0.06
    وثائق
    0.06
     backups
    0.06
     Secure
    0.06
     unless
    0.06
    Act Density 0.007%

    No Known Activations