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

    Neuronpedia

    INDEX
    Explanations

    German studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    When
    -0.06
     Olsen
    -0.06
     fontWeight
    -0.06
     děti
    -0.06
    _steps
    -0.06
    	append
    -0.06
    Algorithm
    -0.06
    jdk
    -0.06
     Overview
    -0.06
     surpass
    -0.06
    POSITIVE LOGITS
     corruption
    0.07
    /models
    0.06
    utilus
    0.06
    فه
    0.06
    .requests
    0.06
    ไข
    0.06
     gören
    0.06
    .Utilities
    0.05
     teslim
    0.05
    πού
    0.05
    Act Density 0.017%

    No Known Activations