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

    Neuronpedia

    INDEX
    Explanations

    any involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mortimer
    0.39
    rett
    0.39
     import
    0.38
     Desenvolvimento
    0.38
     Vir
    0.37
    slab
    0.37
    堃
    0.37
    ERC
    0.37
     незале
    0.36
     מפ
    0.36
    POSITIVE LOGITS
    aspectj
    0.46
    δέ
    0.41
    ῳ
    0.41
     penuh
    0.40
    ດ້ານ
    0.40
    ベ
    0.39
     कुंड
    0.39
    ῶ
    0.39
     AssetImage
    0.39
    ([])
    0.38
    Act Density 0.001%

    No Known Activations