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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure in code excerpts

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

    user prompts and replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.65
    styleType
    -0.62
    AndroidJUnit
    -0.52
     للمعارف
    -0.52
    原始内容存档
    -0.50
    VolleyError
    -0.48
    UrlResolution
    -0.47
     MainAxisSize
    -0.47
    ➞
    -0.46
     &___
    -0.45
    POSITIVE LOGITS
    
    0.50
     daß
    0.43
    Puppy
    0.38
     EconPapers
    0.37
    faßt
    0.37
    wiada
    0.35
    \{\\
    0.35
     Toujours
    0.34
     seti
    0.34
    puppy
    0.34
    Act Density 0.229%

    No Known Activations