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

    Neuronpedia

    INDEX
    Explanations

    Code-related terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teeth
    -0.07
    umes
    -0.07
    _Arg
    -0.07
    ispiel
    -0.07
    十六
    -0.06
     ebook
    -0.06
     sang
    -0.06
    eti
    -0.06
     глаза
    -0.06
     pronounce
    -0.06
    POSITIVE LOGITS
    ("\\
    0.08
     styleUrls
    0.07
    ).\
    0.06
    _contin
    0.06
    ship
    0.06
    
    0.06
    Colon
    0.06
    (interface
    0.06
    413
    0.06
    +"</
    0.06
    Act Density 0.019%

    No Known Activations