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

    Neuronpedia

    INDEX
    Explanations

    jwt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toc
    -0.08
     TextArea
    -0.07
    afs
    -0.07
     Reference
    -0.07
    proc
    -0.07
    督
    -0.07
     txn
    -0.07
    十月
    -0.07
    험
    -0.07
     objs
    -0.07
    POSITIVE LOGITS
     событи
    0.07
    iedade
    0.07
    化进程
    0.07
    ሞ
    0.07
     urban
    0.07
    war
    0.07
    惯例
    0.06
    𝚘
    0.06
    ,SLOT
    0.06
     initi
    0.06
    Act Density 0.001%

    No Known Activations