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

    Neuronpedia

    INDEX
    Explanations

    code, symbols, and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ap
    0.46
    跄
    0.44
    狗狗
    0.43
    Rae
    0.42
    ava
    0.42
    ib
    0.42
    ينات
    0.41
    Compilation
    0.41
    Bound
    0.41
    Hero
    0.41
    POSITIVE LOGITS
    י
    0.52
     measure
    0.51
     자
    0.51
     מד
    0.50
     의
    0.49
     মানুষের
    0.49
    ⸩
    0.49
     사람
    0.47
     환경
    0.46
     세계
    0.46
    Act Density 0.001%

    No Known Activations