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

    Neuronpedia

    INDEX
    Explanations

    Training, jobs, work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Implicit
    -0.07
     sixth
    -0.06
    Completion
    -0.06
    	buff
    -0.06
    (ml
    -0.06
     tourist
    -0.06
    avascript
    -0.06
     stair
    -0.06
    Stephen
    -0.06
    Matthew
    -0.06
    POSITIVE LOGITS
    .Localization
    0.07
     Translator
    0.07
     absolutely
    0.06
    _ajax
    0.06
     disobed
    0.06
     stylish
    0.06
     Trophy
    0.06
     PyObject
    0.06
     navegador
    0.06
    @Configuration
    0.06
    Act Density 0.129%

    No Known Activations