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

    Neuronpedia

    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jíd
    -0.07
    uestion
    -0.06
     等
    -0.06
    �述
    -0.06
     -*-↵
    -0.06
     týd
    -0.06
    901
    -0.06
    DESCRIPTION
    -0.06
    antor
    -0.06
    (!
    -0.06
    POSITIVE LOGITS
     mailbox
    0.27
    mailbox
    0.16
    box
    0.10
    boxes
    0.09
     box
    0.09
    邮箱
    0.08
     mbox
    0.07
    -box
    0.07
    _ty
    0.07
    raz
    0.07
    Act Density 0.003%

    No Known Activations