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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aument
    -0.07
    .tx
    -0.06
    entr
    -0.06
    vm
    -0.06
    限
    -0.06
    .Safe
    -0.06
     Hoch
    -0.06
     nad
    -0.06
     isl
    -0.06
     unpredict
    -0.06
    POSITIVE LOGITS
    Agents
    0.07
    管理员
    0.07
     BOOK
    0.06
     野
    0.06
    .matches
    0.06
    ope
    0.06
     pharmacy
    0.06
     irres
    0.06
     {}↵
    0.06
    Closure
    0.06
    Act Density 0.209%

    No Known Activations