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

    Neuronpedia

    INDEX
    Explanations

    loops and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒈨
    0.44
    жом
    0.42
    anhyd
    0.41
     Giorgio
    0.40
    Bue
    0.40
    न्छ
    0.40
     hydrolysis
    0.39
    𒀊
    0.39
    缛
    0.38
    ♲
    0.38
    POSITIVE LOGITS
     While
    0.50
    ;
    0.49
     while
    0.44
    while
    0.43
     For
    0.39
      
    0.39
    .
    0.39
    ；
    0.37
    ,
    0.37
    While
    0.36
    Act Density 0.030%

    No Known Activations