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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (SQL
    -0.06
    ypes
    -0.06
    arrings
    -0.06
    APP
    -0.06
    ypical
    -0.06
    	Spring
    -0.06
     flawed
    -0.06
     Dark
    -0.06
     Santo
    -0.06
    ürnberg
    -0.06
    POSITIVE LOGITS
    alizace
    0.08
    ाहत
    0.07
    edir
    0.07
     suf
    0.07
     istiyor
    0.07
    .setStatus
    0.07
     │
    0.07
     consulta
    0.06
    Attention
    0.06
    追加
    0.06
    Act Density 0.115%

    No Known Activations