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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variable declarations and control structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "int" followed by "i" or "index"

    np_acts-logits-general · gemini-2.0-flash

    counting integers in loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.90
     חיצוניים
    -0.80
     Administrativna
    -0.74
    principalTable
    -0.70
     InputDecoration
    -0.69
    <bos>
    -0.69
    MethodManager
    -0.68
    
    -0.64
     Wicidata
    -0.63
    StoryboardSegue
    -0.63
    POSITIVE LOGITS
     i
    1.47
     j
    1.07
     ii
    0.89
    i
    0.75
     k
    0.72
    j
    0.72
     я
    0.71
     I
    0.71
    ii
    0.67
     iter
    0.66
    Act Density 0.092%

    No Known Activations