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

    Neuronpedia

    INDEX
    Explanations

    code formatting and style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zimm
    0.73
     Gig
    0.71
     ஆதார
    0.70
    厅
    0.69
    าน
    0.69
     reaffirmed
    0.69
     drowned
    0.68
    耀
    0.68
     marred
    0.67
     Desktop
    0.66
    POSITIVE LOGITS
     camel
    1.06
    func
    0.98
    camel
    0.97
    consistent
    0.95
    no
    0.95
     func
    0.88
     prefer
    0.88
     no
    0.88
    prefer
    0.86
    jsx
    0.85
    Act Density 0.018%

    No Known Activations