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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal identifiers and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     STEELS
    0.48
     alloys
    0.44
     steels
    0.44
     radionuclide
    0.44
     ALLOYS
    0.44
     petitioners
    0.43
    онів
    0.43
     stenosis
    0.43
     galactose
    0.43
     plywood
    0.42
    POSITIVE LOGITS
    .
    0.67
    :
    0.55
    ,
    0.48
    pe
    0.46
    </
    0.46
    code
    0.45
    -
    0.44
    ="
    0.44
    ;
    0.42
    。
    0.42
    Act Density 0.001%

    No Known Activations