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

    Neuronpedia

    INDEX
    Explanations

    Mozilla

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .front
    -0.07
    smarty
    -0.06
     homeland
    -0.06
    OTOR
    -0.06
    	Error
    -0.06
     translation
    -0.06
    .syn
    -0.06
     gauge
    -0.06
    .syntax
    -0.06
    Ids
    -0.06
    POSITIVE LOGITS
    eyh
    0.07
     Jah
    0.06
    대의
    0.06
     festivities
    0.06
     NOTHING
    0.06
     peu
    0.06
    降
    0.06
    าประ
    0.06
     مشتر
    0.06
     McConnell
    0.06
    Act Density 0.001%

    No Known Activations