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

    Neuronpedia

    INDEX
    Explanations

    Foreign language references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imately
    -0.06
     titular
    -0.06
     overflowing
    -0.06
    _nl
    -0.06
    tpl
    -0.06
    컬
    -0.06
    остей
    -0.06
    pent
    -0.06
    ored
    -0.06
    _categorical
    -0.06
    POSITIVE LOGITS
     період
    0.07
     committing
    0.07
     sarà
    0.06
    	Vk
    0.06
     Churches
    0.06
     arom
    0.06
    _SPELL
    0.06
     punishable
    0.06
     potatoes
    0.06
    (validation
    0.06
    Act Density 0.001%

    No Known Activations