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

    Neuronpedia

    INDEX
    Explanations

    Code and language fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     título
    -0.06
    [y
    -0.06
    озвращает
    -0.06
    ›
    -0.06
    Honestly
    -0.05
    should
    -0.05
     Tmax
    -0.05
    Originally
    -0.05
     rw
    -0.05
     muốn
    -0.05
    POSITIVE LOGITS
     Patterns
    0.07
    그
    0.07
    rec
    0.07
    atas
    0.07
     만들
    0.07
     fatt
    0.06
     додатков
    0.06
    .backup
    0.06
    模式
    0.06
    	click
    0.06
    Act Density 0.001%

    No Known Activations