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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Style
    -0.07
     richest
    -0.06
     sağ
    -0.06
     quir
    -0.06
    	append
    -0.06
     disbelief
    -0.06
     incremented
    -0.06
    ीएस
    -0.06
     смеш
    -0.06
     Liz
    -0.06
    POSITIVE LOGITS
     мира
    0.07
    ercises
    0.07
    (owner
    0.06
    ั
    0.06
    .datatables
    0.06
    aille
    0.06
    archivo
    0.06
    ophobia
    0.06
     García
    0.06
    ítica
    0.06
    Act Density 0.025%

    No Known Activations