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

    Neuronpedia

    INDEX
    Explanations

    programming language imports and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused357>
    0.35
    ાર્થ
    0.35
    OLYBD
    0.35
    𢎞
    0.34
     цих
    0.34
     जाप
    0.33
    <unused527>
    0.33
    StarObject
    0.32
    শিষ্ট
    0.32
    spacePad
    0.32
    POSITIVE LOGITS
    ，
    0.46
    ,
    0.46
    -
    0.40
    、
    0.40
     -
    0.39
    ;
    0.38
    u
    0.37
     ,
    0.37
    ↵↵
    0.36
     –
    0.35
    Act Density 0.092%

    No Known Activations