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

    Neuronpedia

    INDEX
    Explanations

    punctuation/grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encodeURIComponent
    -0.07
     ti
    -0.06
    }`;↵
    -0.06
     allocations
    -0.06
    =[]
    -0.06
    امة
    -0.06
     electron
    -0.06
     stool
    -0.06
    codigo
    -0.06
     summarizes
    -0.06
    POSITIVE LOGITS
    ()}
    0.08
     waren
    0.07
     �
    0.07
    .dtd
    0.07
     SINGLE
    0.06
    HR
    0.06
    ософ
    0.06
     случ
    0.06
    _transaksi
    0.06
    (LL
    0.06
    Act Density 0.126%

    No Known Activations