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

    Neuronpedia

    INDEX
    Explanations

    debt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emailing
    -0.07
     kindly
    -0.07
    combined
    -0.07
    _actions
    -0.06
     alle
    -0.06
     dull
    -0.06
    _renderer
    -0.06
    	Editor
    -0.06
    πού
    -0.06
    scatter
    -0.06
    POSITIVE LOGITS
    	export
    0.07
    _dyn
    0.06
    нув
    0.06
     проч
    0.06
    REW
    0.06
    nard
    0.06
    attributes
    0.06
     overturn
    0.06
     unequiv
    0.06
    �ng
    0.06
    Act Density 0.168%

    No Known Activations