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

    Neuronpedia

    INDEX
    Explanations

    data types and structures used in programming, particularly in Java

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

    java and c++ types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     «
    -0.43
     <
    -0.35
    ɵɵ
    -0.32
    1
    -0.32
     „
    -0.32
    fi
    -0.32
    「
    -0.31
     به‌
    -0.31
    2
    -0.30
     fi
    -0.30
    POSITIVE LOGITS
    脚注の使い方
    0.90
    SequentialGroup
    0.79
    0.76
     للاسماء
    0.74
    ſelves
    0.70
     ब्रेकडाउन
    0.69
    aarrggbb
    0.68
     IBOutlet
    0.67
    Obrázky
    0.66
     okuyayım
    0.66
    Act Density 0.007%

    No Known Activations