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

    Neuronpedia

    INDEX
    Explanations

    for loop syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хірур
    0.38
     convoc
    0.38
    surgery
    0.36
    胙
    0.36
    Funk
    0.35
    ádio
    0.35
    RELATES
    0.35
    legate
    0.35
     picnics
    0.35
     Fuk
    0.34
    POSITIVE LOGITS
     loop
    0.92
     loops
    0.84
     structure
    0.80
     structures
    0.77
     statement
    0.74
    结构
    0.74
     Loop
    0.73
    loop
    0.73
     conditional
    0.71
     estructura
    0.70
    Act Density 0.064%

    No Known Activations