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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thoroughly
    -0.08
     slowly
    -0.08
    izzjoni
    -0.08
    态
    -0.07
     indicator
    -0.07
     discrimination
    -0.07
     ọtụtụ
    -0.07
     ఉంటుంది
    -0.07
     الشمس
    -0.07
    icone
    -0.07
    POSITIVE LOGITS
            ↵        ↵
    0.08
     #-
    0.08
    Cause
    0.08
     일을
    0.08
    लब
    0.08
                ↵            ↵
    0.08
     Ramb
    0.07
     Cause
    0.07
     업무
    0.07
     Funding
    0.07
    Act Density 0.001%

    No Known Activations