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

    Neuronpedia

    INDEX
    Explanations

    design codes and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לט
    0.66
     row
    0.65
     rostrum
    0.65
    rows
    0.65
     Christensen
    0.64
     transporter
    0.64
    输
    0.64
    汴
    0.64
     digitization
    0.64
     幅
    0.63
    POSITIVE LOGITS
     codes
    1.62
     code
    1.60
     Codes
    1.59
     Code
    1.58
     कोड
    1.50
    Code
    1.46
    code
    1.46
    Codes
    1.43
     кода
    1.40
     Código
    1.37
    Act Density 0.092%

    No Known Activations